Topics / Coding agents

Coding agents

Start, direct, and review coding agents inside a real project workspace.

An agent can write code, but a product change also needs a running app, a reviewable diff, and a decision about shipping. These articles follow the full loop: open a project, make a bounded request, inspect the result, and keep the context for the next session. Canopy runs supported CLIs in their own terminals; your existing provider account stays with the CLI.

Open this topic's article index for AI assistants →

Guide / 2026-09-28

Why won’t my phone open my local dev site?

Use the computer's LAN address, check the dev server's bind host and port, then trace API calls and HTTPS-only browser features on the phone.

Read →
Guide / 2026-09-28

How do I run Supabase locally with my AI-built app?

Start the Supabase CLI stack, connect the local app to its actual project URL and keys, and verify a test record stays off production.

Read →
Guide / 2026-09-28

Why did Claude Code forget my task after compaction?

Recover a Claude Code task after /compact by checking the actual branch, diff, tests, and lost instructions before giving the agent one verified next step.

Read →
Guide / 2026-09-28

Why did my Trigger.dev task send two emails?

Trace duplicate email through task run IDs, retry attempts, app triggers, and provider events before replaying or changing idempotency settings.

Read →
Guide / 2026-09-28

How do I test a Trigger.dev email task without emailing real users?

Trace one local signup through the Development worker and a test email destination before an agent runs a side-effecting task.

Read →
Guide / 2026-09-28

Why does my AI-built app lose data when I refresh?

Find whether a Save button updates only UI state, browser storage, or a real backend, then test the persistence the product actually needs.

Read →
Guide / 2026-09-28

Is my local AI-built app using the production database?

Trace the browser, API, worker, and database targets before an agent tests writes or migrations in a locally running app.

Read →
Guide / 2026-09-28

How do I keep a coding agent in the right app in a monorepo?

Identify the owning package, shared dependencies, checkout, and run command before an agent edits one feature in a multi-app repository.

Read →
Guide / 2026-09-28

How do I stop a coding agent rebuilding a feature that already exists?

Make the agent locate the active implementation and its callers before editing, then review the smallest change against the running app.

Read →
Guide / 2026-09-28

Why did my coding agent change the lockfile for a small fix?

Trace an unexpected package-lock or pnpm-lock diff to its command and dependency decision, then review and reproduce the PR safely.

Read →
Guide / 2026-09-28

How do I check an AI-built page with a keyboard and screen reader?

Review an agent-built form and dialog with keyboard, accessible-name, error, and screen-reader checks before accepting the PR.

Read →
Guide / 2026-09-28

Trigger.dev runs stuck in dev? Check for a second agent worker

Trace a queued local task across the app, Trigger.dev project, dashboard, and worker processes when two agent worktrees are open.

Read →
Guide / 2026-09-28

What to do when an AI agent opens a 40-file pull request

Inventory an oversized agent diff, separate independent work from dependencies, and rebuild reviewable PRs without losing the original change.

Read →
Guide / 2026-09-28

How do I turn a Figma design into a running page with a coding agent?

Hand an agent one frame, states, assets, and component constraints; run the page in Canopy and review behavior, visuals, and the final diff.

Read →
Blog / 2026-09-28

Canopy 0.3.4: test tab recovery, OpenCode usage, and Remote

A task-based reading of the v0.3.4 release notes with a short installed-build trial for closed tabs, OpenCode Statistics, and Remote continuity.

Read →
Guide / 2026-09-28

Did your coding agent weaken a test to make CI pass?

Review changed assertions, skips, mocks, and browser setup against the original behavior before accepting an agent's green check.

Read →
Guide / 2026-09-28

Why do my agent tests pass locally but fail in GitHub Actions?

Compare the exact PR commit, failing CI step, runner, install, environment, and test command before changing code or rerunning a job.

Read →
Guide / 2026-09-28

How to stop an endless AI code review loop

When each review pass finds another issue, triage findings against the same acceptance checks, verify the latest commit, and decide what blocks this PR.

Read →
Guide / 2026-09-28

Why does my browser show the old app after my coding agent changed the code?

Trace a stale local preview through the checkout, running server, actual port, hot reload, browser cache, and data request before asking an agent to edit again.

Read →
Guide / 2026-09-28

AI-built app works locally but fails on Vercel Preview

Find the first difference between a working Canopy run and a broken Vercel Preview: commit, build, environment, runtime request, or backend target.

Read →
Guide / 2026-09-28

My coding agent committed an API key. What now?

A staged response to an agent-written secret leak: stop propagation, revoke the credential, restore services, inspect exposure, and decide whether Git history needs cleanup.

Read →
Guide / 2026-09-28

How to review an AI-generated access-control PR

Use a permission matrix and cross-user tests to review an agent-written authentication or authorization change before merge.

Read →
Guide / 2026-09-28

Why does my coding agent show so many sent tokens?

Understand large input totals, growing conversation context, cache reads and writes, output tokens, and the checks to make before changing models.

Read →
Use case / 2026-09-28

Canopy vs OpenCode: agent or project workspace?

Compare OpenCode's multi-provider agent, subagents, session stats, and sharing with Canopy's local project workflow around installed CLIs.

Read →
Use case / 2026-09-28

Canopy vs Conductor for parallel coding agents

Compare two full multi-agent workflows across isolated workspaces, local and cloud execution, preview, PR review, team sharing, and platform support.

Read →
Use case / 2026-09-28

Canopy vs cmux for coding agents: terminal control or project workspace?

A dated, source-backed comparison of Canopy and cmux across parallel CLI sessions, attention, browser preview, PR review, remote access, and platform fit.

Read →
Guide / 2026-09-28

Agent session, terminal tab, branch, or worktree: what is the difference?

A practical map of the four things people mix up when running multiple coding agents, with a two-agent example and checkout verification commands.

Read →
Guide / 2026-09-28

Why does my coding agent keep asking for permission?

Diagnose repeated coding-agent approval prompts by checking the action, CLI rules, working directory, and session before changing permissions.

Read →
Guide / 2026-09-28

How to hand an AI-built app to a developer for review

A concrete handoff for founders: reproduce the app, show the exact change, list verified behavior and unknowns, and ask a developer for a risk decision.

Read →
Guide / 2026-09-28

How do I find the command that runs an AI-built app?

A beginner workflow for finding the project directory, runtime, run script, local URL, and first useful error before asking an agent to fix setup.

Read →
Use case / 2026-09-28

Canopy vs GitHub Copilot CLI for coding agents

A dated comparison of Copilot CLI sessions, models, worktrees, review, voice, and remote control with Canopy's multi-CLI project workflow.

Read →
Guide / 2026-09-28

MCP server configured but unavailable to your coding agent?

Diagnose MCP scope, connection, authentication, tool selection, and cross-CLI setup with a read-only documentation server as the example.

Read →
Guide / 2026-09-28

How to inspect an open-source AI IDE before installing it

A repeatable Canopy release check: match installer to tag, verify the asset digest, read source and license boundaries, and test what connects to the network.

Read →
Blog / 2026-09-28

Why cheaper AI tokens can make a coding task more expensive

A worked task-cost comparison that counts retries, cache categories, human review, and accepted code instead of ranking models by input-token price.

Read →
Guide / 2026-09-28

How to set a practical budget for parallel coding agents

Decide how many agents to launch, assign each an output and stop point, then track plan usage, estimates, review load, and accepted work.

Read →
Use case / 2026-09-28

Canopy vs Warp for coding agents: what changes in the workflow?

A dated comparison of third-party CLI agents, worktrees, review, cloud orchestration, team sharing, local data, accounts, and open-source licenses.

Read →
Use case / 2026-09-28

Canopy vs Zed for coding agents: which workflow fits?

Compare Zed Agent, ACP external agents, terminal threads, worktrees, Git, tasks, real-time collaboration, and Canopy's project workflow.

Read →
Guide / 2026-09-28

Can a noncoder build software with AI coding agents?

A realistic first-project path for noncoders: choose a bounded task, run the result, review observable behavior, and know when a developer must check the change.

Read →
Use case / 2026-09-28

Canopy vs Claude Code Desktop: which agent workspace fits?

A current, fair comparison of parallel sessions, worktrees, preview, PR review, remote work, supported CLIs, accounts, and operating systems.

Read →
Use case / 2026-09-28

Can Claude Code and Codex agents talk to each other in Canopy?

Separate cross-CLI messages from Claude-native agent teams, choose teammate models deliberately, and verify a two-session handoff.

Read →
Use case / 2026-09-28

Canopy vs Cursor for coding agents: which workflow fits?

A dated, source-backed comparison of independent CLIs, Cursor Agent, worktrees, review, local previews, remote work, accounts, and pricing boundaries.

Read →
Guide / 2026-09-28

My coding agent edited the wrong branch or worktree. What now?

Identify the actual checkout, preserve every change, move the intended work safely, and verify the correct branch before restarting the agent.

Read →
Guide / 2026-09-28

Debug an agent-built page using the browser console and network log

Collect the exact failing action, console message, request status, service log, and checkout before asking an agent to fix a broken preview.

Read →
Guide / 2026-09-28

How do I ask a coding agent for a demo I can inspect?

A founder-friendly request and acceptance checklist that turns an agent's 'done' message into a running page, observable behavior, and a reviewable diff.

Read →
Guide / 2026-09-28

Share agent work with a team without sharing model accounts

A practical boundary map for shared project context, CLI profiles, team collaboration, model access, and billing in Canopy.

Read →
Guide / 2026-09-28

Which coding-agent CLIs work in Canopy, and what differs?

A dated, source-backed comparison of launch, resume, session signals, shared context, and file attribution across seven CLIs.

Read →
Use case / 2026-09-28

Who can control your coding agent through Canopy Remote?

Understand the PIN, running-host requirement, tunnel, scoped Remote commands, and why terminal access still deserves care.

Read →
Guide / 2026-09-28

How do I run a Trigger.dev worker beside my app in Canopy?

Set up Trigger.dev once, save its dev command beside the website and API, run a dashboard test, and debug the right process.

Read →
Use case / 2026-09-28

What happens to a coding agent when you close Canopy?

Distinguish a closed tab, hidden project, hibernation, app exit, and CLI conversation resume before relying on a session overnight.

Read →
Blog / 2026-09-28

Why an AI coding workspace still needs a real terminal

What a PTY preserves for interactive coding CLIs, what Canopy adds around it, and a quick test for comparing agent workspaces.

Read →
Guide / 2026-09-28

How do I resolve a merge conflict between two coding agents?

Find the conflicting branches, compare each agent's intent, make one integration decision, and test the combined behavior.

Read →
Guide / 2026-09-28

When a coding-agent session suddenly burns through usage

Pause the session, separate context growth from repeated work and stale estimates, then restart with a smaller verified scope.

Read →
Use case / 2026-09-28

From GitHub issue to agent draft PR: a reviewable handoff

Read the whole ticket, give one agent a scoped branch, test the running change, and close the loop with evidence in the PR.

Read →
Use case / 2026-09-28

Turn a screenshot or rough idea into a coding-agent task

Capture the evidence, investigate before editing, write a bounded acceptance check, and review the resulting draft PR.

Read →
Guide / 2026-09-28

Research a codebase question without changing code

Choose an answer, source-backed investigation, or implementation task deliberately, then keep findings available for the next decision.

Read →
Use case / 2026-09-28

Find the old agent session, then resume the right project

Recover a past decision from search, verify the branch and PR, restart local services, and resume only the session that still helps.

Read →
Guide / 2026-09-28

Share project instructions across Claude Code and Codex

Place durable facts, CLI-specific instructions, reusable skills, and MCP connections where each agent can actually use them.

Read →
Use case / 2026-09-28

Which coding agent needs me? Triage several live sessions

Avoid replying in the wrong terminal: identify project, checkout, branch, waiting question, and next decision before steering an agent.

Read →
Guide / 2026-09-28

Why a new agent worktree cannot build: env files and dependencies

Diagnose missing .env files, local packages, Python environments, ports, and shared services before blaming the coding agent.

Read →
Use case / 2026-09-28

Canopy vs VS Code for coding-agent work

A practical comparison of real CLI sessions, worktrees, PR review, local previews, and the editor features you may still need.

Read →
Guide / 2026-09-28

Measure AI coding cost per accepted change

A repeatable worksheet for comparing model choices by accepted work, review time, retries, token categories, and provider charges.

Read →
Guide / 2026-09-28

How to give a coding agent useful visual feedback

Turn a vague 'this looks wrong' into a page, viewport, element, expected behavior, and screenshot an agent can act on.

Read →
Guide / 2026-09-28

How do I test an AI-built UI before merging it?

Review the running page across viewport sizes, interaction states, console and network errors, keyboard use, and the latest PR diff.

Read →
Use case / 2026-09-28

How do I stop two agent worktrees from using the same port?

Keep each branch's local preview distinct, identify the process behind a URL, and compare the right running app with the right diff.

Read →
Guide / 2026-09-28

Switch from Claude Code to Codex without losing the task

A cross-CLI handoff when usage limits, model choice, or review needs change: preserve the goal, branch, evidence, and next action.

Read →
Use case / 2026-09-28

What leaves your machine when you use Canopy?

A plain-language map of local workspace data, coding CLI traffic, optional GitHub and team services, remote tunnels, and on-device dictation.

Read →
Guide / 2026-09-28

The coding agent says done, but the app is still broken

A recovery workflow: reproduce the failure, inspect local services and logs, point the agent at evidence, and verify the new diff.

Read →
Guide / 2026-09-28

An AI coding-agent task brief you can copy and use

A bounded brief with context, acceptance checks, constraints, and a handoff format for Claude Code, Codex, or another coding CLI.

Read →
Guide / 2026-09-28

AI-generated pull request review checklist and reviewer prompt

A practical checklist for intent, changed files, risk, tests, UI behavior, comments, and the final diff, with a copyable reviewer brief.

Read →
Guide / 2026-09-28

Git worktrees for parallel coding agents: commands and cleanup

Create a separate branch and directory per coding agent, check status, integrate reviewed work, and remove worktrees safely.

Read →
Use case / 2026-09-28

Share agent work with a team without sharing AI accounts

A host, implementer, and reviewer handoff through Canopy Team: project chat, files, review requests, disk ownership, and separate model accounts.

Read →
Guide / 2026-09-28

Keep coding-agent context useful between sessions

Make a handoff that preserves the task, decisions, branch, and evidence without carrying an entire chat transcript forever.

Read →
Use case / 2026-09-28

Can I use voice with a coding agent in Canopy?

Choose between Canopy dictation, a CLI's own voice input, and hands-free conversation; turn a spoken issue into a checked task and review its result.

Read →
Use case / 2026-09-28

Terminal, tmux, or Canopy for coding agents?

Compare the actual jobs: running a CLI, keeping sessions alive, isolating edits, starting services, and reviewing agent work.

Read →
Guide / 2026-09-28

How to reduce coding-agent token usage without losing the result

Scope tasks, manage growing context, choose models deliberately, and compare accepted work rather than chasing a low token count.

Read →
Use case / 2026-09-27

Run Claude Code and Codex side by side without losing the work

A concrete two-agent workflow with separate checkouts, clear ownership, shared project context, and one final review.

Read →
Use case / 2026-09-27

Resume a local coding agent from your phone

Use Canopy Remote to inspect a running project, reconnect after a phone disconnect, and steer the right agent without repeating a task.

Read →
Use case / 2026-09-27

Review an agent-written PR, address comments, and fix CI

A review loop from intended behavior to final diff, including draft findings, feedback, conflict resolution, and checks.

Read →
Use case / 2026-09-27

How do I start my website, API, and worker with one click?

Run a downloadable three-process project: save its commands, watch a worker change the API count, inspect the preview, and verify the agent's edit.

Read →
Guide / 2026-09-27

How to set up Canopy and run your first AI coding agent

Install an agent CLI, open a project in Canopy, run the app, and review your first change. Includes a downloadable practice project.

Read →
Guide / 2026-09-27

How to run multiple coding agents without losing track

A two-agent workflow with task ownership, separate worktrees, service ports, attention checks, and a final review decision.

Read →
Guide / 2026-09-27

How to review an AI-generated pull request

A review workflow for agent-written code: inspect the diff, ask for a risk map, address comments, fix CI, and merge deliberately.

Read →
Guide / 2026-09-27

Run a website, API, and background worker in one workspace

Configure project run commands once, then start, inspect, and restart your local development stack from Canopy.

Read →
Blog / 2026-09-27

A workspace for people who direct AI agents

A practical founder workflow for directing a coding agent: define one outcome, run the product, inspect evidence, and hand off risky decisions.

Read →
Blog / 2026-09-27

Understanding AI coding agent usage and estimated cost

Read Canopy's CLI, model, session, plan-limit, and estimated-cost views without mistaking a token estimate or stale quota snapshot for a provider charge.

Read →
Blog / 2026-09-27

Your AI coding cost dashboard is not your bill

Separate the three ledgers behind a coding-agent dashboard: model consumption, plan capacity, and actual provider charges.

Read →
Guide / 2026-09-28

Did your coding-agent skill actually load? A five-minute test

Separate skill discovery, invocation, and useful execution with an explicit test, a natural-language test, and one negative control.

Read →
Guide / 2026-09-28

Review a coding-agent skill before your team shares it

Inspect a borrowed SKILL.md, its scripts, tool access, and test behavior before making a repeatable workflow available to every agent.

Read →
Use case / 2026-09-28

Can Canopy work offline with a local coding agent?

Test local files, Git, services, Preview, search, and a preinstalled CLI against the separate requirement for a local model endpoint.

Read →
Use case / 2026-09-28

What do file claims solve when coding agents share a repository?

Use visible file ownership to catch overlapping plans early, then verify checkout isolation, actual edits, and the final integrated diff.

Read →
Guide / 2026-09-28

Why won’t my dev server start in Canopy?

Trace a failed website, API, or worker launch through its checkout, command, first error, port, dependency, and observed URL.

Read →
Guide / 2026-09-28

Which coding-agent session introduced this regression?

Trace a reproducible failure through the running build, Git history, pull request, and related agent session before assigning a fix.

Read →
Guide / 2026-09-28

Coding agent stuck or waiting for input? Check the live session

Distinguish a pending decision, active tool, running dev server, completed turn, and failed agent before interrupting or restarting.

Read →
Use case / 2026-09-28

Canopy vs Devin Desktop (formerly Windsurf) for coding agents

A dated comparison of multi-agent coordination, installed CLIs versus ACP, local previews, review, cloud handoff, and account boundaries.

Read →
Guide / 2026-09-28

Coding agent hit a usage limit mid-task? Save the work first

Identify the actual limit, preserve the checkout and partial result, then resume, wait, or hand off without repeating work or changing accounts blindly.

Read →
Use case / 2026-09-28

Canopy vs Superset for parallel coding agents

Compare two local agent workspaces across worktrees, persistent processes, app runs, browser preview, PR review, Remote, and license terms.

Read →
Guide / 2026-09-28

How to evaluate an AI coding workspace on a real project

A repeatable trial for terminal, IDE, and multi-agent workspaces that follows one change from setup through running behavior, review, resume, and accepted result.

Read →
Use case / 2026-09-28

Canopy vs Replit Agent for building an app

Compare a hosted AI app builder with a local multi-CLI workspace across first setup, parallel tasks, preview, GitHub, deployment, team access, and usage.

Read →
Guide / 2026-09-28

Work on a Lovable app locally in Canopy without losing Git sync

A branch, environment, preview, and publishing checklist for using local coding agents on a Lovable project connected to GitHub.

Read →
Guide / 2026-09-28

Keep building a Bolt app with local coding agents in Canopy

Connect Bolt to GitHub, isolate an agent change, check the app's backend and run commands, merge in GitHub, and verify Bolt and the live site.

Read →
Guide / 2026-09-28

v0 not showing your local agent's GitHub changes? Check the branches

Trace a local Canopy agent change through GitHub, v0's base and working branches, Pull Changes, preview deployments, and production permissions.

Read →
Use case / 2026-09-28

Canopy Remote, Claude Code, Copilot CLI, or SSH from your phone?

Choose a remote coding-agent workflow by host state, CLI coverage, project evidence, access rules, and what you can actually verify on a phone.

Read →
Guide / 2026-09-28

Run OpenCode with a local Ollama model in Canopy

Set up a local model route, account for OpenCode V1 and V2 differences, verify context and tool use, then test an offline coding task in Canopy.

Read →