Free during early access · No credit card

Your team runs on AI tools.
You have no idea what they're doing.

Conduct gives every team lead spend visibility, policy enforcement, and a full audit trail — across every AI coding tool your team uses. Plus 22 ready-made agent workflows, DORA-lite metrics, and per-agent scorecards — so you can see what's working, not just what's running.

Sign in with Google, GitHub, or Microsoft · Connect your existing stack

Projects DevOps Story → shipped PR
Draft
Blocks
Trigger
starts a run
Agent Step
reason + act
Action
direct API call
Approval
wait for human
Notify
send output
Guard
enforce policy
TRIGGER
Story ready
Linear
approve
AGENT STEP AI
Generate code
Sonnet · 14 tool calls
ACTION
Push + draft PR
GitHub
APPROVAL
Await reviewer
Slack
Run trace
Story ready
0.0s
Guard check
0.1s · passed
Generate code
48s · Sonnet
Run tests
22s · 218 pass
Push + draft PR
3.1s · #1294
Await reviewer
waiting…
22 ready-made agent templates Human approval before every merge Hard cap per developer Full audit trail · SOC 2 ready MIT licensed · open source
Setup in minutes

Live on day one.

Connect your stack, install a playbook, and your first agent run goes through Guard automatically.

01
🔗

Connect your repo

Link GitHub and Slack. Add credentials in Settings → Environments. No migration, no new tooling — Conduct wraps around what you already use.

02
📦

Install a playbook

Browse 22 pre-built agent playbooks. Click Install — the canvas is pre-wired. Add your credentials and the agent is ready to run.

03

Get output in Slack

PRs, reviews, triage comments, incident diagnoses — delivered to Slack. Every run passes through Guard automatically. Approve or reject in one click.

What Conduct does

Three pillars. One platform.

Agent Workflows

Stop doing the same work around every PR. 22 pre-built playbooks handle issue triage, code review, incident response, and release notes — with human approval before anything ships. Every agent gets an A–F scorecard and DORA-lite metrics so you know what's actually delivering value.

Browse Marketplace →

ConductGuard

Your developers are spending money on AI tools you can't see into. Guard gives you real-time spend per developer, policy enforcement, and a full audit trail — across every AI tool, from one dashboard.

See the full Guard story →

Agent Memory

Agents that improve with every run. Before acting, each agent recalls what it learned on this repo. After the run, it records the outcome. The 10th PR is smarter than the first.

Memory docs →
Platform architecture

Triggers in. Outcomes out.
Everything auditable in between.

Conduct sits between your existing tools and your AI agents — routing events through agent templates, enforcing Guard policies, and recording every decision.

GitHub event
Slack message
PagerDuty alert
Linear ticket
CI/CD failure
Manual trigger
Trigger → Agent Engine
Conduct Agent Engine
Agent Template → Agent → Run → Auditable trace
Brain blocks
haiku sonnet opus
Action blocks
GitHub Slack Linear
Guard layer
BLOCK WARN AUDIT
Outcomes
🔀
GitHub PRs
Draft fix, review request, or merge — human approves before ship
💬
Slack alerts
Incident summaries, Guard blocks, run completions
🔍
Audit trail
Every run, every block, every approval — immutable, linked
🧠
Agent memory
Each run writes back — agents improve with every execution
🔌

Agents and external tools connect via the Conduct MCP server — query runs, trigger workflows, and check Guard policy state from any MCP-compatible AI tool. conduct mcp install wires it in 30 seconds.

Agent Templates

One click to install.
Running in minutes.

18 pre-built agent templates across 10 categories. Browse, install, configure credentials, run.

Issue → PR

Autopilot + Approval

Issue labeled ai-ready → AI implements fix, runs tests, opens PR → human approves in Slack before merge.

⚡ Issue labeled9 blocks4.8k installs
Code Review

PR Reviewer

PR opened → AI reviews the diff for bugs, security issues, and style → posts a structured review comment.

⚡ PR opened4 blocks5.2k installs
Security

Security Scanner

PR opened → OWASP Top 10, secrets, auth bypass scan → posts a security findings report to the PR.

⚡ PR opened5 blocks2.7k installs
CI/CD

CI Failure Alert

Build fails → AI diagnoses the failing step, finds the root cause → posts a structured fix to Slack.

⚡ Build fails4 blocks2.2k installs
Triage

Issue Triage

New issue opened → AI classifies type and priority, adds labels, asks clarifying questions if vague.

⚡ Issue opened4 blocks3.6k installs
Incidents

Incident Responder

Alert fires → AI correlates recent deploys and commits → posts a root-cause hypothesis to #incidents.

⚡ PagerDuty webhook7 blocks1.1k installs
Browse all 18 agent templates →
ConductGuard

Every AI tool. Every developer.
One policy.

AI spend is now a board-level concern. Guard gives your VP Eng and CFO spend visibility, policy enforcement, and a full audit trail — across every AI coding tool your team uses.

👁️

No visibility

Which developer spent $800 on Claude last month? Which project burned your budget? Today, you can't answer these questions.

🚫

No policy

Developers run destructive commands in production environments, push secrets to AI context, deploy without review. Uncontrolled.

📋

No audit

When something goes wrong, there's no record of what the AI did, what was approved, or who authorised it.

Spend visibility
Per developer
Tokens + cost per dev, per tool, per day
Policy enforcement
BLOCK / WARN / AUDIT
Three modes — from hard stop to silent log
Audit trail
Every AI call
Linked to the run that triggered it
Set once. Enforced everywhere.
Step 1 · Team lead

Set the policies

Define spend caps, blocked commands, approved tools, and enforcement mode in the Guard dashboard. One config. Applied automatically to every developer.

Step 2 · Developer

Accept invite, log in

Team lead invites developers from the dashboard. Developers log in — policies download and apply to their local environment automatically. No IT ticket. 30 seconds.

conduct login
Step 3 · MCP

Guard in every editor

The conductguard-mcp server connects Guard to Claude Code, Cursor, Windsurf automatically.

Claude CodeCursorWindsurfAider
Agent Memory

Agents that get better
with every run.

Most AI tools start from scratch every time. Conduct agents remember. Before each run the agent recalls what it learned on this repo. After the run it records the outcome.

🧠

Recall before acting

Before the agent block runs, a Memory read block retrieves the most relevant past summaries using vector similarity — not just recent history, but what's most applicable to this exact task.

📝

Record every outcome

After the run, a Memory write block stores what was done: the approach, files changed, what worked. That becomes context for future runs on the same repo.

🔒

Scoped and isolated

Each playbook builds its own knowledge store per repo. What Autopilot learns on conductai/api never bleeds into conductai/web. Two scopes: repo or workspace.

Spec-Driven Development

AI writes code fast.
Too fast.

Without a spec, AI coding tools drift. Requirements get lost. Nobody can trace which code maps to which decision. SDD gives every AI action a why — and Conduct enforces it automatically.

Generate your spec free

Describe what you're building. The agent asks 3 questions and writes a structured SPEC.md with numbered, testable FR-xxx requirements. No account needed.

Generate SPEC.md →

Scaffold your repo in one run

sdd-bootstrap reads your SPEC.md and commits 6 files to your repo — AGENTS.md, DESIGN.md, PLAN.md, SPRINT.md, CLAUDE.md, and the spec index. Fully wired in minutes.

See the full workflow →

AI can't ship without a spec

A pre-merge hook blocks any PR where changed files have no FR reference. The only platform that enforces spec traceability at the git layer — not just stores requirements.

Learn about enforcement →
FR numbers sync with GitHub Issues Jira · soon Linear · soon
Going deeper

Built to be honest.

Open source tools for developers. An honest comparison with every major AI engineering tool.

Open source tools

Agent Booster cuts per-request AI costs by up to 15× by sending only the relevant code. Claude Code Team Kit gives your whole team a shared setup in one command. Both free, MIT licensed.

Browse open source tools →
⚖️

AI tools, compared honestly

How does Conduct compare to GitHub Copilot, Devin, CodeRabbit, LinearB, and others? Honest feature matrix, strengths, trade-offs, and a decision guide for your team's situation.

Compare all tools →
Early adopters

Teams shipping faster.

"Labeled a bug at 5pm on a Friday. PR was open by 5:02pm, tests green, ready to review Monday morning. That's the thing — it just works while we're not watching."

E
Engineering Lead
Series B startup · 35-person eng team

"Guard paid for itself in week one. I could finally see exactly which developers and which tools were burning our Claude budget. We cut spend by 40% without slowing anyone down."

V
VP Engineering
SaaS company · 60-person team

"The Copilot reviewer playbook caught three hallucinated API calls in AI-authored PRs that our human reviewers missed. We won't merge AI code without it now."

S
Senior Engineer
Growth-stage startup · 12-person eng team

Try it in 30 seconds.

Sign in, connect a GitHub repo, install your first playbook. Running in under 5 minutes.

No credit card · Connect your existing tools · Sign in with Google, GitHub, or Microsoft