Tool change log
New releases, pricing and capability changes of coding tools and agents, in chronological order.
Viewpoint
November 2026 · 15
GitHub Copilot impact dashboard adds chat and VS Code agent usage, code review gets API controlstech leadUse the new dashboard data to measure how much your team actually uses Copilot's agent and chat features.Google Cloud adds OpenAI models and Codex agents to Model GardenCTOOpenAI models can also be used within Google Cloud, which may reduce vendor fragmentation.GitLab 19.5 makes agentic development a governed part of its DevOps platformtech leadPlatform-level agent support could standardise how the team uses agents.AWS launches Kiro bots to coordinate AI coding agentstech leadDivision of work between agents is gaining tool-level support; factor this in when planning orchestration.Cognition launches SWE-2 Flash to make coding agents cheaper and fastertech leadThe cheaper, faster model is worth piloting on routine tasks, given budget constraints.Xcode 27.3 adds GitHub Copilot to its built-in assistantsenior developerApple-platform developers can now use Copilot in Xcode too, so it is worth comparing it with the built-in assistant.Anthropic restricts Claude Code from cloning video gamessenior developerIf you give the agent game or reverse engineering work, expect a refusal, and keep an alternative tool or a manual approach at hand.tech leadCheck whether the new restriction affects your team's game, compatibility or reverse engineering tasks before you build a process on them.startup founderIf your product idea relies on recreating existing games or software, a provider rule change is a business risk.OpenAI may stop supplying models to Cursor from 12 Novembersenior developerIf you use OpenAI models in Cursor, check which model you can switch to before 12 November.tech leadAssess which team workflows depend on the Cursor–OpenAI relationship, and prepare a switchover plan.OpenAI to pool ChatGPT and Codex usage allowance from Decembersenior developerCodex and chat draw on one allowance, so schedule heavy agent tasks deliberately.tech leadRecalculate the team's subscription allowance, because Codex use will crowd out other ChatGPT use.Coding agents get spending limits as Cognition adds hierarchical budgets to Devintech leadSet budgets at team and task level, and define what happens to an interrupted agent task.Android Studio opens to any AI coding agent, ending Gemini exclusivitysenior developerIn Android Studio you can use your preferred agent, so it is worth comparing them on your own project.tech leadThe ACP standard reduces vendor lock-in, so choosing an agent can be more flexible at team level.Google is shutting down one of its AI coding toolssenior developerIf you build on Google's tool, find out the shutdown date and switch to another tool in good time.tech leadKeep vendor attrition risk in mind when choosing tools.Qodo builds context into AI code review with Codextech leadAssess whether context-based review produces fewer false alarms than your current tool.Anthropic adds message threads to its API, but the token bill stays the samesenior developerIf you build your own agent on the Claude API, threads may speed up response times, but do not expect lower costs.startup founderToken costs have to be optimized another way, because threads help with latency, not with the bill.GitHub Copilot Fusion picks models automatically; local preview runs only partly on-devicesenior developerDo not assume your code stays entirely local, because other stages of the process do not run on your machine.
October 2026 · 72
DeepSeek unveils proactive coding agent prototype to challenge AnthropicCTOAnother competitor could put pricing pressure on the coding-agent market, but the prototype is not yet production-ready.senior developerProactive agents raise new questions about access and oversight.Anthropic releases tool that reports to managers whether employees work efficientlytech leadUsage reports can also be used to measure team performance, so privacy and trust rules need to be set.CTOMeasuring developer performance with AI carries a risk of distorted metrics.Microsoft's new tool can cut AI coding costs by up to 31%CTONew tools can cut AI coding costs, but 31% is only an upper bound, so teams need to measure their own savings.Google shuts down Jules coding agent; data export open until November 11senior developerJules users must export their data by November 11 and choose a new agent.tech leadThe shutdown shows why a toolchain should let teams swap out providers.Claude Code and Codex start blocking game cloning and reverse engineeringsenior developerAn agent may refuse reverse-engineering or cloning tasks, which should be factored in when designing workflows.startup founderThe rule may reduce the risk of AI-based cloning, but does not eliminate it entirely.Mistral's open-weight Le Chonk model ranked alongside Codex GPT-6.1 Terra in codingCTOA strong coding model that can run on your own infrastructure may reduce vendor dependence and data-retention risk.GitHub adds 4 million CPU cores and 160 PB of storage as AI code surge strains capacityCTOAgent-generated traffic also strains platform capacity, so it is worth planning a fallback.Copilot Studio's GitHub Copilot harness becomes the Microsoft Copilot harnesstech leadGiven the rename and the opening, it is worth reassessing whether a custom agent can be built on Microsoft's harness.Anthropic adds Claude Code option to delete files without approvalsenior developerBefore enabling it, set up a version-controlled or isolated working directory where deletions can be restored.AWS Transform can be used in GitHub Copilot via MCP for .NET projectssenior developerA .NET migration or modernization task can also be started from Copilot via MCP.GitHub launches Copilot Fusion, which picks and routes models for each tasktech leadCompare Fusion's cost and quality with your current fixed model choice, and update the team's Copilot settings accordingly.CTOAutomated model selection affects licence and token cost planning, so budgets need to be recalculated.senior developerModel choice is taken out of your hands, so check which tasks Fusion handles with predictable results.GPT-6.1 Terra arrives in GitHub Copilot, ChatGPT and Codexsenior developerThe model can be selected in Copilot; compare it with the previous model on your own codebase.tech leadMeasure the effect of the model change on the team's own tasks before making it the default.Former GitHub CEO launches rival platform built for AI coding agentsstartup founderA repository service built for agents offers an alternative to GitHub and is worth trying.CTOWhen considering a platform switch, weigh the long-term risk and integration with agents.OpenAI reverses ChatGPT Pro Codex cut and doubles usage limitssenior developerOn the Pro subscription the Codex allowance is not reduced and in fact increases; on the Plus plan it is unchanged.CTOWhen comparing subscription and API costs, account for the doubled limits.Google opens Android Studio to more than 40 third-party coding agentssenior developerOn an Android project, developers can use their preferred agent directly in the IDE.tech leadAgent choice can be standardised across the team, and the Android CLI allows automation in CI as well.Copilot gains Agent Merge, Automations and agents in Dev Containers with VS Code 1.137senior developerAgent Merge could replace manual fixing of pull requests, but the changes still need to be reviewed.GitHub to retire old Teams app, some Copilot models and expiring gh tokens on November 16senior developerIf you use a Copilot model that is being retired, switch to a supported one.GitHub Copilot comes to Teams, and Azure DevOps to Microsoft Copilottech leadPermission and review rules for code changes started from chat should be defined in advance.Recursive launches Flint, a free coding model that runs on laptopssenior developerTry it in a local environment to see how usable a laptop-run model is on your own codebase.CTOLocally run models can reduce API costs and the risk of data leakage, so they are worth evaluating.startup founderA free, local model can lower the entry cost of prototype development.JFrog launches local AI security for developer laptops to detect shadow AICTOThe list of approved AI tools and how they are managed should be assessed with shadow AI in mind.Docker, Pydantic AI and Google ship tools to run AI agents in isolated environmentsCognition says Devin Fusion scores 68 on coding agent index at 31% lower costCTOWhen evaluating agents, compare cost per task and the model combination, not just the score.tech leadRun a pilot on your own codebase, because the vendor's claims rest on an independent benchmark.VS Code 1.143 makes Copilot the default, adds AI model bake-off and local AI without creditstech leadSet the new defaults and agent controls at team level.CTOReview enterprise settings and the rules governing model selection.senior developerUse the model comparison feature to measure which model works better on your own tasks.Claude Code and Codex CLI updates: compression, MCP tasks, mid-reply steeringsenior developerAfter the updates, try mid-reply intervention so an agent that is editing the wrong file can be stopped in time.tech leadWith MCP support expanding, the internal tool integrations of agents should be re-evaluated.OpenAI to offer GPT-6 Astra and Codex through Google Cloud Model GardenCTOWhen purchased through Google Cloud, OpenAI models can be managed under an existing cloud contract.JetBrains releases Air for five IDEs and ThinkRail, an open-source agentic IDEsenior developerDevelopers using JetBrains IDEs can try several agents in one interface, and ThinkRail's open code can be inspected.tech leadFor a solution that integrates several agents into one IDE, access and cost management should also be assessed.GitHub AI Scan now covers PHP in pull requests; Snyk agent turns vulnerabilities into PRsGemini Enterprise renders MCP Apps in chat as Google publishes developer guidesenior developerInteractive interfaces for MCP-based internal tools can be built inside Gemini Enterprise.tech leadIt is worth building on the MCP standard if tools must be made available across several platforms.Replit switches default model partner from Anthropic to OpenAIstartup founderFor products built on platforms, a change of model provider can alter quality and cost, so a fallback provider should be planned.tech leadReplit projects should be retested after the model change to check how they behave.OpenAI shows better code generation in low-resource languages and for COBOL migrationsenior developerFor migrating legacy systems (e.g. COBOL), AI assistance is worth trying, with the output checked by tests.CTOCost estimates for legacy-modernization projects are worth recalculating in light of the new models.GitHub outlines "ambient intelligence" direction with physical Copilot controlstech leadGitHub's direction is worth following, but the practical value of physical controls should be tested in your own environment.JetBrains: IntelliJ code intelligence brings 20–30% efficiency gain to Claude Code and Codexsenior developerTry connecting the agent to an IDE-level code index so it uses fewer tokens and makes fewer mistaken searches.tech leadExamine how you could wire an IDE-level symbol index into your agents' workflow.Anthropic makes Code Review in Claude Code generally availabletech leadTry it with one team and compare the bugs it finds with your current review results.senior developerAI review can work well as a first-pass filter, but final approval should stay with a human.BAND and Parallax desktop apps manage multiple AI coding agents in one placetech leadIf your team uses several agents, look into a unified management interface and logging options.GitHub: the future developer interface is ambient intelligence, not more AI buttonstech leadWatch Copilot's direction and consider how it fits your team's tooling strategy.GitHub Copilot retires six models on October 19, more deprecations due in Novembertech leadTest the switch on your team's typical tasks before the old model disappears.Gemini 4 Argon now available in GitHub Copilotsenior developerTry it on complex tasks and compare the results with the model you used before.tech leadAssess the model's cost and quality against your team's tasks.Google brings its AI coding platform to the Gemini app on Macsenior developerTry it on a Mac to see whether it fits your current toolchain.GitHub makes AI Scan metrics, Agentic Autofix and AI secret detection generally availabletech leadLet autofix suggestions through only with human review.Anthropic built its own source control for AI-scale code volume, but it is not availableCTOAI-generated code volume carries an infrastructure cost; plan for CI and storage capacity.tech leadSet limits on the number of branches and PRs that agents open.OpenAI Codex: 500K context, next-message prediction, Dots agents, usage limitssenior developerOn large codebases you can try the larger context, but watch how quickly the limits are used up.CTOFactor in the weekly and 5-hour limits if your team plans heavy Codex use.Copilot administration: model and MCP controls, server-side settings, organization billingCTODecide on the cost model for Copilot code review: organization billing or member quotas.AI code review: Atlassian splits it between two agents, JetBrains proposes a three-tier reviewtech leadDefine what the AI checks and what humans check, and tailor the review process accordingly.senior developerUse the AI reviewer for pre-screening, but keep logic and architecture checks for yourself.Google AI Studio lets users build Android apps without code, from age 18 and without a developer accountstartup founderYou can use it for quick prototypes, but a production product still needs maintainable code and a security review.QA testerExpect vibe-coded apps to spread, and to appear without having been tested.Local AI coding: JetBrains Mellum 2.1, Junie on RTX Spark, OpenCode with Ollamasenior developerTry the local model on routine tasks and compare its quality with cloud-based tools.startup founderRunning locally can cut API costs, but it comes with hardware costs.MCP support arrives on platforms: Apigee hybrid, Google MCP Toolbox, .NET guidesenior developerWhen building an MCP server, grant narrow permissions for database and API access.Copilot: multi-repository Slack and Teams, mobile and web remote control, Ollama models in the CLItech leadClarify within the team which repositories are approved for Copilot work started from chat.senior developerWhen using remote control, check permissions and make sure the agent's work can be traced.Is the one-million-forint Ghost Core local AI computer for developers worth the price?startup founderCalculate the payback of local AI hardware against API costs.Lovable offers EU inference to control where AI requests are processedstartup founderYou can cite processing within the EU as an argument when EU customers have data-handling expectations.CTOCheck where your AI tools process data.JetBrains releases Mellum2.1, a 12-billion-parameter open MoE coding modeltech leadAs an open model it can run on your own infrastructure for coding agents, so it is worth comparing with closed models.CTOA smaller open model can reduce dependence on external providers.Databricks Lakebase proposes branching databases for coding agentssenior developerUse a separate database instance for agent runs.GitHub Copilot comes to Windows with local models and sandboxed tools; what goes to the cloud is unclearCTOThe privacy benefit of local execution holds only if the scope of data sent to the cloud is known.Claude Haiku 5.5 arrives in GitHub Copilot and Cursortech leadFor short, simple tasks, it is worth configuring the cheaper model and measuring quality.CTOSwitching models can significantly reduce tooling costs on short requests.OutSystems Agent Experience opens to Claude Code and CursorCTOExternal coding agents can be used on a low-code platform too, under governance controls.tech leadOutSystems teams can try their own agent tools on the platform.Codex Auto-review goes free for ChatGPT users as GitHub changes Copilot review billing and Anthropic opens Claude Code Review betatech leadAI review is now available from three providers, so it is worth piloting them on cost and impact.CTOBecause of the organization-level billing settings for Copilot code review, the budget needs to be set in advance.QA testerAutomated review can be used to pre-screen pull requests, but it does not replace your own checks.GitHub Copilot desktop app expands, with preview control of desktop applicationstech leadWith the plan expansion, teams on Business subscriptions can try the app; set the usage rules first.Silicon Labs brings AI to embedded development; Google Cloud releases MCP Toolbox Java SDK 1.0senior developerIn Java environments, MCP Toolbox 1.0 now provides a stable basis for agent data access.tech leadAn embedded team can try the beta SDK, but should wait for a mature version before production use.Update your IDE to restore agent activity in Copilot usage metricstech leadCheck usage reports for gaps before basing adoption or cost decisions on them.Agent pull requests overtook human ones on GitHub in August as Copilot moves to usage-based pricingtech leadGiven the share of agent PRs, review capacity and PR rules need to be redesigned.CTOWith usage-based pricing, Copilot costs depend on load, so a spending cap should be set.senior developerMore agent PRs need to be reviewed, so review priorities should be set down in writing.OpenAI adds invisible watermarks to ChatGPT and Codex text in the EUtech leadAssess to what extent text and code generated with Codex and delivered to EU customers is affected by the watermarking.CTOThe compliance policy should specify how AI-generated content is handled in the EU.GitHub launches ReviewBench, an open benchmark for AI code reviewtech leadAn open yardstick is now available for comparing code review tools; it is worth using in purchasing decisions.QA testerThe benchmark helps evaluate how well AI reviewers detect defects.CTOAn independent benchmark can be used to check vendor claims before purchase.GitHub Copilot routes requests across models with HydraFusion, cutting estimated cost by 67% on cheapest pathCTORouting between models is one way to cut AI tooling costs and is worth building into the cost model.tech leadThe 67% figure is an estimate, so measure it against your own workload before it goes into the cost plan.OpenAI's always-on Dots agents can start Codex work, raising usagetech leadDelegated Codex work counts against the plan allowance, so usage should be monitored.CTOThe cost of always-running agents should be planned in advance.OpenAI starts 28-day Codex improvement pledge with daily fixestech leadCodex can expect rapid improvement and speedups, but tracking changes and version control matter.senior developerDaily updates may change Codex's behavior, so critical workflows should be checked.Claude Code accepts mods from version 2.1.287 that can alter panels and tool callssenior developerMods let you customize Claude Code, so usage and CI status can be made visible.Qodo 3.0 brings enterprise quality control to agentic software developmentQA testerA new enterprise tool is available for automatically checking AI-written code.tech leadThe tool can be evaluated as a complement to the review process.Together Link runs open models inside Claude Code; Together AI says coding costs could fall by over 50%startup founderOpen models can cut agent costs significantly, but quality has to be measured.tech leadTools can be made model-agnostic, which reduces vendor lock-in.MCP becomes the standard, but token consumption and testing infrastructure remain gapssenior developerThe token cost of MCP servers has to be measured, because large tool descriptions consume the context.tech leadTesting and cost-measurement practices need to be set up for MCP servers.AWS GovCloud adds support for Claude Code and Claude 5.5 for regulated workloadsCTOAnthropic's tool is now available in regulated environments too, so the compliance plan should be reviewed.Copilot code review gets API support and a new default effort leveltech leadReview how PR review depth and cost change under the new default, and build the API into your workflow.Anthropic's Claude Code mods make its behavior customizable; managed machines load a security mod firstsenior developerWrite custom hooks and mods to eliminate recurring annoyances.GitHub Copilot can now work with desktop apps through computer useQA testerTry it for UI testing of desktop applications, but check its reliability.
September 2026 · 80
Google unveils Gemini 4 Argon, a frontier model for coding and cyber defencesenior developerWatch for access to open up, and test it on coding tasks.AMD launches Ross, an agentic AI assistant for embedded developerssenior developerOn an embedded AMD platform, try the assistant built on environment-specific knowledge.OpenAI's Agents API offers Codex harness as a service with computer use; data stored only in USCTOEU data-handling requirements may make US-only data storage a dealbreaker; compare it with the Bedrock alternative.startup founderWork out whether the Codex harness offered as a service is worth it compared with building your own agent framework.OpenAI DevDay: Codex gets reusable cloud environments that work across devicessenior developerTry the cloud Codex environment for long tasks that run without a laptop, and measure the time saved on repeated setup.tech leadExamine the built-in security scans as a complement to your existing code-review process.CTOWeigh the data-handling and cost implications of cloud execution before rolling it out team-wide.Codex CLI adds parallel agents, voice control, enterprise controls and mid-run steeringsenior developerUse mid-run steering so you don't have to restart long agent runs.JetBrains Air brings agentic coding with team-level governancetech leadCheck whether team-level governance replaces per-tool agent rules.CTOFor JetBrains shops, this is a governed agentic alternative.Replit Agent gets looser model controlsstartup founderWeigh the cost and quality impact of model choice in Replit prototypes.Nvidia launches open agent safety platform backed by more than 100 companiesCTOAdd agent security to procurement and risk-management criteria, as an industry standard may be taking shape.Microsoft redesigns Copilot with Home, Code and Autopilot; main features are usage-basedCTOAllow for cost swings from usage-based pricing when planning licensing.tech leadAssess whether Code and Autopilot replace your existing Copilot workflows.Claude Sonnet 5.5 released and now available in GitHub Copilotsenior developerTest it on your own codebase for speed and quality against the previous model.CTOExamine the effect of the cheaper model on your AI tooling budget.Cognition cuts Devin prices, adds ChatGPT sign-in and iPhone appstartup founderWith the price cuts and subscription compatibility, you can recalculate Devin's cost-effectiveness.senior developerBesides Cloud, Desktop and CLI, you can now supervise Devin's tasks from your phone.Wix's Base44 launches Base Code and a cloud workspace to take on Claude Code and Cursorstartup founderIt is another alternative among AI coding tools; compare it on price and integration.senior developerTry the cloud workspace for prototypes.A GPT-6.1 Sol megjelent a GitHub Copilotban, a GPT-6 Sol a Codexbensenior developerCompare the effect of switching models on your everyday tasks before you move over.Cursor adds Slack-connected team bots, deployment monitoring and PR vulnerability detectiontech leadA shared Slack bot can standardize how your team uses agents.Claude Code cloud sessions open to all users; overtime mode draws on weekly limitsenior developerPlan your weekly usage allowance, because extra work is drawn from it.Arm launches AI portal to optimize models for 22 million developerssenior developerFor models intended for Arm devices, the optimization portal is worth trying.Codex moves to token-based billing from April, with credits and plan limitsCTOCost depends on usage, so plan a budget and set up alerts.tech leadMeasure the team's token consumption before choosing a plan.Claude Code's AGENTS.md support reportedly forced users to choose between privacy and the featuresenior developerAfter the fix, check how telemetry and instruction-file loading behave.Claude Code no longer cuts off a task at the 5-hour limitsenior developerCan start a long task more calmly even close to the limit.tech leadPlan the team's agent usage around the limits.GitHub turns on several Copilot features by default for Business and Enterprise planstech leadInform the team about the new defaults.Flux expands platform to show whether AI coding investments are paying offCTOA tool for measuring the cost and impact of AI coding.tech leadMay help link tool usage to outcomes.Microsoft rebuilds Copilot with Home, Code and Autopilot, and up to 50% discountsCTOReview Copilot licences, as the plans are being restructured and discounts are available.tech leadCompare the new Code and Autopilot features with the current toolset.startup founderThe discounts may lower the cost of AI coding, but also look at the usage-based fees.Claude Opus 5.5 arrives in Claude Code, with pricing tied to longer coding sessionssenior developerTry the model on long, multi-step tasks and check the results.tech leadEstimate costs based on the pricing for longer sessions.CTOBear in mind that the cost of longer runs may develop differently.JetBrains reorients its products around agentic development: Air, Junie and Air Governancetech leadEvaluate Air Governance for central control of agent use.senior developerTry Junie in your existing JetBrains IDE workflow.CTOA new vendor option for the managed adoption of AI coding.Copilot updates: OpenTelemetry, JetBrains, unified inline model, Canvas UI, autofix with memorysenior developerReview the new editor features and how autofix uses memory.Cognition brings Devin coding agent's cloud sessions to the terminalsenior developerCan also start and follow cloud Devin sessions from the terminal.Zoho adds agentic AI controls to Catalyst platform for production software developmenttech leadEvaluate Catalyst's controls for using agents in production.Microsoft sees AI agents, local models and Linux as the way to win back developerssenior developerIn Windows development environments, expect local models and Linux integration.Grok 4.7, GPT-6 Sol and Luna and Opus 5.5 reach Copilot and Codex; six models retiredtech leadCheck that the team does not rely on the models being retired on 19 October, and switch in good time.senior developerCompare the new models on your own tasks before making them the default.Agent platform race: Cursor and OpenAI coordinators, Atlassian, AWS, Cloudflare, Moonshot, AntigravityCTOThe vendor landscape is splitting quickly, so consider an open, swappable agent layer.tech leadAssess cheaper or local-model options on your own tasks.senior developerTry at least one alternative agent alongside your current one.Anthropic brings Cloud Sessions to Claude Code, with credits for subscriberssenior developerTry out parallel sessions running in the cloud and use the subscriber credit.tech leadAssess how well cloud sessions fit into the team's review and CI processes.startup founderThe credit makes cloud agents cheap to try for a smaller team.GitHub Copilot adds cost and quality controls, and Code Review gains agent capabilitiestech leadSet a budget and an approval process for extra credits, and try out agentic Code Review.CTOCredit-based billing requires cost oversight, and the new controls can help with that.senior developerAgentic review can complement manual review, but it does not replace it.Claude Code now reads AGENTS.md, and auto mode safety checks are freesenior developerA single AGENTS.md is enough to maintain for several tools; a separate Claude-specific file is not required.tech leadStandardize the instruction file across repositories so the team stays tool-agnostic.GitHub Copilot leaves the IDE: shared coding agents arrive in Teams and Slacktech leadDecide where agents should be allowed into team chat and who can approve their changes.senior developerAgentic review will take place in chat, so traceability of decisions must be preserved deliberately.OpenAI Agents API in public beta: the Codex harness for cloud agentssenior developerCan build a Codex-based cloud agent into their own product.startup founderA managed agent runtime, with no infrastructure of your own.GitLab tightens rate limits on AI coding traffic, affecting free and unauthenticated usesenior developerIn agent-based workflows, plan for request-rate limits.GitLab joins other providers in imposing rate limits on AI coding agentstech leadPlatform limits must be factored in when scheduling agent traffic.CTOBecause of platform restrictions, AI agent capacity should be planned vendor by vendor.Claude Code Projects: persistent cloud session that delegates work to multiple agentssenior developerLong, multi-step tasks can be delegated to cloud agents, but the results still need to be reviewed.tech leadRunning agents in parallel requires rules for access and for accepting results.Cloudflare security audit skill turns AI code review into an adversarial workflowsenior developerMulti-agent verification can be adopted in your own AI review process.Unity launches official Codex and Claude Code plugins to keep AI agents off outdated tutorialssenior developerIn Unity projects, installing the plugin gives the agent a current, official source of knowledge.tech leadIn game development teams, the official plugin reduces errors caused by outdated APIs.GitHub Copilot plugin to end support for older JetBrains IDEssenior developerJetBrains users need to update their IDE version for Copilot to keep working.Copilot budget increase requests now generally available, adding another AI consumption unit to tracktech leadThe team also needs to follow the budget increase request process and unit-based consumption.CTOManaging AI costs is more complicated with new consumption units, so budget limits should be reviewed.Working group releases 'Skills over MCP' specification for agentic workflowssenior developerAlongside MCP servers, it is worth learning about the standard distribution of Skills.tech leadCustom agent integrations should be aligned with the standard to reduce vendor lock-in.Claude Code weekly limit drops: the '25% increase' was in effect a 17% cutjunior developerThe weekly allowance may run out faster, so long agent runs should be planned more deliberately.senior developerScheduling of large agent tasks needs to be adjusted to the tighter weekly allowance.tech leadMeasure the team's actual Claude Code consumption again before planning a sprint on the old allowance.CTOChanges to provider limits are a cost and predictability risk, so it is worth keeping a fallback tool.OpenAI opens the Codex harness to developers as a managed Agents APIsenior developerFor building their own agents, developers can use the Codex harness through the API, so the control layer does not have to be written.tech leadIn a build-versus-buy decision, the API is an alternative to maintaining an in-house harness.CTOBuilding on a harness service creates vendor dependence, so an exit strategy should be clarified.startup founderAn agent product can be built faster without in-house orchestration, but the cost model should be checked in advance.GitHub Copilot auto model selection gains cost and quality modessenior developerDevelopers should set when a stronger model is needed and when a cheaper one is enough, depending on the task.tech leadThe team-wide default mode should be chosen based on measurements of cost and code quality.CTOAutomatic routing allows vendor-independent model use, which serves as a tool for cost control.Copilot Cowork and Copilot Studio add natural-language app buildingtech leadDefine in advance how apps built by non-developers will be governed.CTOInternal low-code/no-code app building requires cost and security rules.Sourcegraph makes Agentic Batch Changes generally available for large codebasessenior developerAgent-based bulk changes can be used for refactoring across monorepos or many repositories.tech leadPlan the review process for bulk code changes in advance.Anthropic adds plugin evals to Claude Code with six grader types, a no-plugin baseline and a CI gatesenior developerThe effect of skills becomes measurable against the no-plugin baseline.QA testerEvaluation tests can be written for the agent's behavior.OpenAI launches Agents API in public beta, putting the Codex harness behind a single API callsenior developerInstead of building your own agent orchestration, the hosted Codex harness can be tried and compared with an in-house solution.tech leadInternal tools built on the API may be faster to develop, but vendor lock-in and cost limits should be weighed in advance.startup founderAn agent-based product can be built with less infrastructure, but platform dependence grows.Cognition says its SWE-2 coding agent matches rivals at a fraction of the costCTOThe vendor's benchmark and cost claims should be checked on your own tasks before deciding on a model switch.tech leadA pilot should compare quality and running costs against the current agent.Atlassian upgrades its AI coding agents for always-on software developmenttech leadWith agents running continuously, the rules for accepting contributions need to be clarified.TestMu AI adds mobile automation to Kane CLI with natural-language testsQA testerMobile tests can be written in natural language, but reproducibility must be checked.Unity launches official Claude Code plugin with 29 engine skills and live Editor controlsenior developerIn Unity projects the agent can control the Editor directly, so the permissions it needs are worth reviewing.junior developerUnity-specific skills offer a faster start, but the generated code still has to be understood.Microsoft urges organizations to build and publish apps with CopilotCTOGovernance and security review of apps built by non-developers must be set up in advance.Coder Agents becomes generally available, offering fully self-hosted AI codingDevelopers can rent Anthropic infrastructure, saving weeks of workstartup founderLess in-house infrastructure is needed for an agent-based product, at the price of greater vendor dependence.Enterprise-managed sandbox arrives in Copilot for JetBrains IDEsAnthropic promised 20x more usage, but developers hit a weekly capsenior developerBecause of the weekly cap, long agent jobs must be scheduled, or a fallback model kept ready.tech leadPlans with a visible cost ceiling are more predictable for the team.Students get a free year of AWS Kiro, and GitHub Copilot is also free for themjunior developerNewcomers can try agent-based tools for free, so this is now a basic skill.GitLab Duo Self-Hosted now supports bringing your own model through Microsoft FoundryCTOIn regulated environments, the choice of model and the location of the data can be kept in-house.Cohere releases its first coding model, targeting developersCTOA new vendor has entered the coding-model market and can be an alternative where sovereign AI is a requirement.Lovable introduces drafts for testing app changes before going livestartup founderEven for apps built with AI, experiments can be kept separate from the live version.Copilot code review can approve pull requests without human review, off by defaulttech leadSet a policy on whether AI approval may be enabled and for which risk levels of change.senior developerThe role of human review is changing, but human approval remains mandatory for critical changes.GitHub Copilot HydraFusion preview combines multiple models and picks the model automaticallysenior developerYou no longer have to pick a model by hand, but it is worth tracking which model did the work and checking the result.tech leadThe cost and compliance impact of automatic model selection should also be reviewed at team level.GPT-6 Astra is available in ChatGPT Plus only in Work and Codex, at a higher price per tokensenior developerMeasure on your own tasks whether fewer iterations really make up for the pricier token.tech leadBase the cost model on total cost per task, not on the token price.Google releases Gemini 3.8 Flash, now in the Copilot model pickersenior developerAs a fast, cheaper model, it can be tried in Copilot for repetitive coding tasks.GitHub launches Copilot desktop app with parallel agentssenior developerRunning several agents in parallel can speed work up, but it increases the volume of changes to review.tech leadPrepare for the review load and branching strategy that parallel agents bring.Copilot team AI credits cut by up to 44% at an unchanged priceCTOThe effective unit price has risen, so the Copilot budget needs to be recalculated.tech leadTrack credit consumption and schedule expensive agent tasks more sparingly.Microsoft engineer says typing code is over as Aspire gets agent-friendly CLIsenior developerIn .NET, agents can control Aspire applications through the CLI and MCP.Harness launches AI code review and rebuilds its Git repository for agent traffictech leadAI code review can help with the review bottleneck if false alarms are measured.JetBrains renews TeamCity with AI and MCP supportZoho opens Catalyst cloud to AI coding agentsSlack Code brings ChatGPT, Claude and Copilot into developer collaborationtech leadThe permissions and logging of agents launched from chat channels need to be governed.Cursor becomes unavailable in Russia: lost features and alternativessenior developerIn the affected region, developers need to switch to an alternative editor or model.Project Zenith: special Windows 11 edition coming for AI developerssenior developerFor Windows-based AI development, it is worth watching for the edition's release and requirements.GitHub Copilot app adds parallel agent sessionssenior developerIndependent tasks can be given to agents in parallel, but the results must be reviewed separately.tech leadParallel runs increase consumption and review load, so set limits.Copilot code review can now approve pull requeststech leadDecide whether a Copilot approval counts toward required reviews, and in which repositories it can be disabled.senior developerHave a human look over approved PRs too, especially for security and business logic.Anthropic launches Claude Fable 5.1 and Mythos 5.1, now available in GitHub Copilotsenior developerFor long-running, agent-based tasks, it is worth comparing the new model with the current one on your own codebase.tech leadIt is available in the Copilot model picker, so the team's default model can be re-evaluated on cost and quality.Claude Code and Cowork can control a user's Mac in the backgroundsenior developerThe concise output style can reduce token use, which also helps with the weekly limit.
August 2026 · 74
Claude Code weekly limit rises 25%, but reports say real capacity falls 17%senior developerBefore 14 September, measure your actual weekly consumption and reschedule long agent runs.tech leadRedo the team's Claude Code quota planning and designate a fallback tool for when the limit is hit.CTOThe cost model is changing, so recalculate licence costs and the split between tools.startup founderIf development relies on a single tool's limit, a tighter quota can slow delivery.AI coding tools move to usage-based pricing: Copilot credits and token ratesCTOMonthly AI cost now depends on usage, so introduce budgets and reporting.tech leadGive the team a rule on when a premium model may be used and when a cheaper one is enough.senior developerSave premium models for hard tasks and use a cheaper model for routine work.startup founderDeveloper tooling costs now scale with usage, so choose between Copilot, Cursor and Claude Code on cost.Google unveils Gemini 3.8 Flash and a security-focused Cyber variant with stronger codingsenior developerAs a cheap, fast coding model, it can be compared with current tools.tech leadA measurement on your own codebase should decide whether switching is justified.OpenAI Codex has 25 million active users; GitHub Copilot reaches 50 millionCTOAI coding tools have gone mainstream, so tool choice is a vendor-strategy question.tech leadA large user base means a fast feature pace, so re-evaluate tools every six months.Anthropic's Compliance API gives more visibility into Claude CodeCTOFor enterprise rollouts, identity and compliance controls are now available.VS Code: August Copilot releases and 1.135, which gives agents a second opinionsenior developerTry the new agent features on your own codebase and see how much the second opinion improves results.tech leadCoordinate the team's VS Code and Copilot settings before updating.MCP ecosystem expands with Docker catalog, Rocket.Chat server and Chrome DevTools, while security lagssenior developerMCP servers are worth trying, but access should be restricted to the minimum.GitHub reopens new signups for Copilot Business and EnterpriseCTOIf a Copilot rollout stalled because of the restriction, procurement can restart now.tech leadLicence requests from waiting teams can now be submitted.New coding tools: xAI's Grok Build CLI and a free, high-limit Google assistantsenior developerFree or cheap alternatives are worth trying if price or usage limits are tight.startup founderA free assistant can cut development costs, but its data-handling terms should be checked.AMD releases ROCm 10 with ROCm.AI and an Agent Skills packagesenior developerFor AMD GPU development, an agent using the official skills may produce more accurate code.OpenAI tests an always-on 'Persistent' mode for Codextech leadPrepare for agents that run continuously, and define oversight and stop rules.OpenAI restores 5-hour Codex and Work limits for ChatGPT Plus userssenior developerPace Codex use within the limits, or move to a higher plan if your workflow requires it.tech leadFactor the limits into team planning and check whether the more expensive plans pay off.startup founderDo not base cost plans on the discounted limits.Anthropic raises Claude Code and Opus API rate limits, citing SpaceX Colossus 1 dealsenior developerCheck the new limits that apply to your own plan, as the increase is not the same for everyone.tech leadReassess how much load parallel agents and long sessions can take.CTOTake the provider's capacity expansion into account when choosing vendors.Codex agents reach office apps in the $20 ChatGPT Work planCTOExpect non-developer staff to automate with agents too, and set rules for their data access.startup founderCodex can now be used for workflow automation, not just programming.Salesforce launches Slack Code to bring AI coding agents into shared team channelstech leadAssess whether channel-based agent use improves team transparency, and set who is allowed to start an agent.senior developerIn a shared channel, the agent's requests and results are visible to everyone, so put a review rule on it.GPT-5.6 comes to AWS Kiro as OpenAI cuts its priceCTOCompare the new prices with your current model costs and reassess model choice.tech leadGPT-5.6 can be tried in Kiro; it is worth measuring price-performance on your own tasks.startup founderFalling model prices can improve the unit economics of agent-based products.Copilot harness reaches general availability in JetBrains; Copilot Studio billing starts September 1CTOPrepare a cost estimate for Copilot Studio harness agents before billing starts on 1 September.tech leadAssess which agents are built on the Copilot harness and how much they are used.senior developerThe harness is now available in JetBrains IDEs and can be tried out.JetBrains' Junie Local runs the AI coding agent fully offline on a Macsenior developerThose whose code cannot leave the machine can try local running if memory is sufficient.CTOCompare the hardware cost with cloud subscriptions.Cursor launches Origin, a GitHub alternative for code hosting built into its editortech leadAssess whether consolidating code hosting, review and agents on one platform is worth it, and what the migration cost is.CTOConsider vendor lock-in, especially after Cursor's change of ownership.A GitHub Copilot megjelenik a Microsoft Teamsbentech leadDecide whether to allow Copilot in Teams channels and which repos it may access.senior developerCode requested in a chat needs review just like any other Copilot output.MCP publishes new roadmap focused on long-running processes and AI agent authenticationtech leadSupport for agent authentication and long-running tasks may influence how MCP servers are designed.senior developerFollow changes to the MCP specification if you are building your own server.OpenAI cuts developer pricing for frontier GPT-5.6 Sol model by more than 20%startup founderRecalculate the AI cost per request and consider whether to switch to a cheaper model or put the savings toward margin.CTOThe price change is a reference point in vendor negotiations and in the cost budget for coding agents.Azure DevOps remote MCP server reaches general availability without Claude, ChatGPT or Cursor supporttech leadWhen choosing an MCP server, check which agents are supported.GitHub Copilot's monthly usage hits record high after new pricing modelCTOUnder the new pricing, track teams' actual consumption, because costs can rise with usage.tech leadPermissions and usage need to be monitored to avoid unexpected bills.Slack Code brings AI agents and coding together in shared channelstech leadVibe coding in shared channels makes work more transparent, but it requires permission and review rules.Anthropic extends Claude Code weekly usage boost through August 31tech leadBefore the bonus expires, assess the team's actual usage so that limits returning to normal do not stall work.startup founderThe higher allowance lasts only until the end of August, so it should not be treated as permanent when planning costs.Anthropic tokens cost more on Vercel, and non-English prompts may add hidden costsstartup founderCheck the actual token price of using a model through a platform, and the cost of non-English prompts.tech leadMeasure token cost by platform and by language before budgeting.Claude Code now available with a self-hosted runner for Docker and GitHub ActionsClaude Code's new /design command creates UI mockups in the terminalsenior developerThe command can be tried for quick UI sketches, but the output must be reviewed against the design system.junior developerTerminal-based mockups speed up the start of frontend tasks, but decisions should rest on the team's existing components.Replit launches Free Mode powered by OpenAI's GPT-5.6 Luna modelstartup founderIt can be tried at no cost for building prototypes, but usage terms and data handling should be checked before scaling.junior developerA free entry point for quick experimentation, though checking the generated code remains the developer's responsibility.Warp launches Warp Factories, bringing the AI-factory model to software developmenttech leadFor workflows handed to agents, define gates and metrics before the team works in a factory model.Cursor launches Origin code hosting platform as GitHub suffers outagetech leadTry Origin on a small project and measure how much is gained from tighter integration between the editor and the repository.CTOTying code hosting and the AI tool to one vendor creates a new supplier dependency that should be weighed in strategy.GitHub Copilot gets Canvases, Slack and Teams integrations and a new apptech leadBecause coding tasks can be started from chat, you need rules on who may launch agents from team channels.senior developerCanvases help track an agent's steps, so they are worth building into the review process.xAI's Grok 4.6 model now available in GitHub Copilot for enterprise developerstech leadDecide in the admin settings whether to enable the model, and compare it with the others on smaller tasks.Google halves Gemini 3.7 Flash API prices as coding scores improvestartup founderThe cheaper Flash model could be an alternative to pricier models for simpler coding tasks, so it is worth benchmarking on your own workloads.senior developerBenchmark on your own codebase before switching models based on published scores.Can Copilot fix its own security findings? Testing GitHub agentic autofixsenior developerSuggested patches must be validated with tests before they are merged.DeepSeek quadruples its rates and takes on Claude Code with a new modelstartup founderCost models built on DeepSeek need to be recalculated with the higher rates.CTOThe price advantage of the cheap alternative may shrink, so plans to switch models should be re-evaluated.Grafana's gcx CLI and MCP server reach general availabilitysenior developerFor debugging, the agent can be given real data, which can lead to more accurate suggestions.Claude to watermark generated code and text, and developers push backsenior developerCheck that the watermark does not interfere with build, lint or licensing processes in code written by Claude.tech leadSet a rule for how the team handles marked, AI-generated code in the repository and in client deliveries.CTOAssess the legal and contractual impact of watermarking if you deliver Claude-built code to clients.startup founderConsider what marked code means for investor due diligence and IP representations.Google's Gemini 3.7 Flash targets coding and agents with a 50% introductory price cutsenior developerTest an agent task with Gemini 3.7 Flash alongside your current model and compare the quality.CTORecalculate agent costs, but keep in mind that the price cut is introductory.startup founderThe cheaper Flash model could lower the token costs of coding agents if the quality is sufficient.Cursor releases Origin, a Git host for fleets of AI agentstech leadAssess whether agent fleets need a separate Git host or whether your current platform is enough.New models arrive in GitHub Copilot: MAI-Code-1.1-Flash and Grok 4.6senior developerCompare the new models on your own codebase before replacing the default model.tech leadRecord which models are approved for the team, since the options differ in both cost and quality.CodeRabbit offers cheaper NVIDIA model and application-level security scanningtech leadMeasure whether the cheaper model maintains review quality.Claude Code's auto mode to become the default, with fewer human approvalssenior developerReview which actions auto mode permits in your own repositories, and explicitly set the forbidden commands before the default takes effect.tech leadDecide at team level whether auto mode stays the default, and record the approval rules in the shared configuration.junior developerThe agent can carry out steps without asking, so check your own changes before committing.Spotify launches Xirp, a single interface for Claude Code, Codex and Gemini CLIsenior developerTry running multiple agents in parallel in one interface, and check whether the agents work on the same file state.tech leadLook at how a multi-agent workflow can be standardised across the team.Microsoft merges Copilot into a single app, adds paid Autopilot agent tierCTOAssess the licensing and data-handling implications before budgeting for the Autopilot tier.tech leadCheck how GitHub Copilot's place changes within the unified product family.Meta's Muse Code is cheaper but, by its own admission, weaker than Claude Codetech leadRun a benchmark on your own tasks that includes token costs, because a cheaper agent is not always cheaper in the end.CTOAdd Muse Code to your evaluation of agent vendors, but do not switch on price alone.senior developerTry it on routine tasks, where weaker performance matters less.AI-generated code raises quality and maintainability risks, says Info-Tech; GitHub launches Code Qualitytech leadSet up quality gates and maintainability metrics for AI-generated code.senior developerDo not accept AI code without tests and an explanation, because technical debt surfaces later.CTOIntroduce measurement of how much AI code is merged and with what defect rate.OpenAI and four rivals publish Agent Plugins, a common extension formatsenior developerIf you write plugins for agents, look at the format, since one package can run in several tools.tech leadFactor the format into tool selection, as it lowers switching costs.GitHub Models service shut down as developers switch to OpenAIsenior developerIf you build on the GitHub Models API, find your dependencies and plan the migration.Weekly agent roundup: Cursor reportedly building 'Sand', Claude Code learns to launch a simulatorQA testerLook at how an agent that launches the simulator on its own could be used to automate mobile and UI testing.senior developerFollow how the agents' runtime environment is expanding, and when it makes sense to involve them in debugging.Platforms integrate: Atlassian context engine, MongoDB, AWS Continuum, Semgrep–Replittech leadCheck that the context sources agents use do not leak sensitive data.Developer platform updates: Copilot web controls, Java SDK, JetBrains memory and ACPsenior developerIn JetBrains environments, try the agents that connect via ACP and local Ollama models.tech leadIf your team works in Java, look at the Copilot SDK for building your own tools.Stateless Model Context Protocol could reshape agent infrastructuresenior developerAvoid MCP server designs that depend on session state if the new approach becomes widespread.Five AI rivals back a shared plugin standard for developerssenior developerA plugin written to one standard can be used across several agent tools.tech leadWhen choosing tools, lock-in risk falls if the plugin layer is standardised.Claude Code sessions can message each other and run on team-controlled infrastructuresenior developerParallel agent sessions can be coordinated, making it possible to split up more complex tasks.CTORunning on your own infrastructure is one possible way to reduce data and compliance risk.Microsoft releases open-source unit test agent for Copilot CLI and VS CodeQA testerValidate agent-generated tests with mutation or coverage checks before trusting them.senior developerTest generation can be tried on existing modules to complement hand-written tests.Copilot code review adds agent skills and MCP; impact dashboard gets ROI sectiontech leadSkills and MCP can be plugged into code review, and the dashboard's ROI data can be used to justify costs.CTOThe ROI view can help you judge whether Copilot licences are justified.Meta launches Muse Code coding agent to compete with Claude Code and CodexCTOGiven the pricing, it is worth running a cost-performance comparison against the current agent vendor.tech leadMuse Code can be piloted on a small, well-defined scope alongside the existing Claude Code or Codex.startup founderA cheaper agent could cut token and subscription costs, but vendor lock-in should also be weighed.Anthropic unveils Claude Code Security to find and fix code bugssenior developerProposed fixes must be validated with tests and review.Microsoft makes GPT-5.6 Sol the default in GitHub Copilot for its own stafftech leadMicrosoft's internal model choice may signal the likely direction of the default Copilot model.Copilot: credit complaints, token budget and new Lite and Balanced tiersCTOCopilot costs need to be recalculated based on the credit model and the new tiers.tech leadIntroduce a per-developer token or credit budget and a policy on model choice.senior developerRestrict the use of expensive models to tasks that genuinely need them.startup founderLocal LLMs or API-based billing can be considered as alternatives.AWS launches Kiro Crew, an autonomous orchestrator for 24/7 coding agentstech leadDecide which tasks can be given to unsupervised agents and where human review remains mandatory.CTOThe cost and accountability model for continuously running agents should be settled before deployment.senior developerThe centre of gravity of the work shifts toward defining agents' tasks and reviewing their results.OpenAI Codex arrives on Amazon Bedrock and gets a security API connectionCTOIn AWS environments, Codex can be tried out within an existing cloud contract.OpenAI says today's Codex will feel "primitive" by falltech leadPlan tool choices around a short review cycle, because capabilities change quickly.CTOFavour a flexible, swappable agent layer over long contracts.GitHub to deprecate Spark on github.comtech leadPrototypes and projects built in Spark must be saved before the deprecation.Auto Mode to become the default in Claude Codesenior developerWith automatic approval as the default, you need to review which commands may run without confirmation.tech leadPermission rules and prohibited actions should be set at team level before the new default takes effect.Microsoft adds new agent harness to Copilot Studio, with GitHub Copilot also arrivingtech leadAssess whether Copilot Studio agents could replace custom-built automations.CTOFor an agent-platform decision within the Microsoft ecosystem, this is a new factor.Security vendors build defences around coding agents: AWS Continuum, Wiz, SailPoint, Menlo, Snyk, MicrosoftCTOProtecting agents requires a separate budget line.MCP expands: stateless updates, Webflow intent-driven APIs, MapQuest and TripSuite serverssenior developerFor agent-friendly APIs, intent-driven design is better than simply wrapping endpoints.Open coding models close in on the frontier: DeepSeek V4 Pro scores 80.6% on SWE-bench, Qwen3.8-Max claims 16-day runtech leadOpen models that can be run in-house are realistic alternatives and are worth comparing on your own tasks.CTOOpen models put pressure on the pricing of closed vendors.Atlassian introduces an AI-native software development system in Jiratech leadA backlog managed in Jira can also be handed to agents, which makes the quality of task descriptions critical.CTOAgent integration within a single platform may reduce the number of tools.OpenAI's $230 Codex Micro macropad puts agent controls on your desksenior developerPhysical buttons can speed up approving and directing the agent for heavy Codex users.Port builds a control layer for AI-powered software developmentCTOWhen agents are in use, a platform-level control layer may be needed.