The accountability layer for AI agents.
Autonomous agents are powerful — and unpredictable. Agent Bob wraps any agent in enforceable rules and a verifiable pin, so you can prove what it will and won't do before you put it in front of anyone.
AGENT BOB
I keep every agent accountable.
The industry is racing to make agents more autonomous and more capable. Almost no one is making them accountable. The result: agents that act in ways you didn't intend, say things you never approved, and leave you no way to prove what happened. Capability without governance isn't an asset — it's exposure.
Agent Bob is the layer the agent platforms skip. You define what an agent is allowed to claim and do; Agent Bob turns that into a governance package and seals it with a verifiable pin. Now the agent's behavior isn't a hope — it's something you can point to.
Define the rules
What the agent can claim, what it must never do, how it discloses itself, when it hands off to a human.
Generate the governance package
Agent Bob compiles your rules into a structured, pinned artifact.
Pin and verify
Every package gets a cryptographic fingerprint, so anyone can confirm exactly which governed version is in play.
The missing layer
Other platforms optimize autonomy and capability. Agent Bob adds the part they leave out: governance you can verify.
Bound to the package, not the prompt
Your rules aren't polite suggestions buried in a prompt — they're compiled into the governed artifact the agent is tied to.
Verifiable, not vibes
A cryptographic pin proves which governed version ran. No 'trust us.'
Works alongside your stack
Keep building agents however you like. Agent Bob governs the ones that face customers, partners, or the public.
Any agent whose mistakes would cost you.
Customer support
Keep answers inside policy.
Operations & internal tools
Bound what an agent can touch and claim.
Research & analysis
Require sources, prevent confident fabrication.
How governance works
Every governed agent is defined by a manifest (the approved rules and claims), kept honest by grounding (it operates inside that manifest), and sealed with a pin (a sha256 fingerprint of the exact version).
The approved rules, claims, and identity definitions.
Ensures the agent operates only inside that defined manifest.
A SHA-256 fingerprint that verifies the exact version running.
More autonomy shouldn't mean less control
Most AI agents loop until the budget runs out — or never stop at all. Agent Bob lets you set hard limits before your agent runs, and signs them so they can't be quietly changed.
Hard bounds
Cap iterations, spend, and run time. The loop can't go past what you set.
Stall detection
If your agent spins in circles or stops making progress, it halts instead of burning budget.
Human in the loop
When a limit is hit, hand the decision to a person instead of letting the agent push on blindly.
Tamper-evident
Your limits are cryptographically signed into the agent's policy, so no one can loosen them after the fact.
Agent Bob governs any agent — one function, many jobs. Sales Bob is the done-for-you sales vertical — one job, many products.
Both run on
ClawMaven— same governance standard.
Common questions
What is Agent Bob?
+
Agent Bob is a friendly onboarding tool that helps non-technical teams design a governed AI agent. You answer plain-language questions and Bob generates a deployment-ready governance package backed by ClawMaven governance.
What is a governed AI agent?
+
A governed AI agent is an AI agent that ships with explicit rules: which tools it can use, when a human must approve an action, how much it can spend, what data it can remember, and how its activity is logged. Agent Bob produces these rules as a 7-file governance package.
How do I govern an AI agent with Agent Bob?
+
You walk through a 7-step wizard: pick an industry and agent pattern, set personality and tone, choose tools, define autonomy and loop limits, set budget and usage caps, configure memory rules, and set approval gates. At the end, Bob compiles everything into a pinned governance package you can deploy.
What is loop governance and why does it matter?
+
Loop governance is Agent Bob's way of preventing an agent from running out of control. You set hard limits on iterations, run time, and spend. If the agent stalls or hits a bound, it halts or escalates to a human instead of burning budget or making unchecked decisions.
Can Agent Bob stop an AI agent from running forever?
+
Yes. You set hard bounds on iterations, run time, and spend. If the agent exceeds any limit, it stops automatically. You can also enable stall detection so the agent halts if it stops making meaningful progress.
What is a tamper-evident policy for AI agents?
+
A tamper-evident policy means your limits and rules are cryptographically signed into the agent's governance package. If anyone tries to change them after the fact, the signature breaks and the mismatch is detectable. This makes agent behavior provable, not just promised.
What happens when an AI agent reaches its limit?
+
You choose the outcome in advance: halt stops the agent completely, while escalate hands the task to a human for review. Either way, the agent does not push past the boundary you set.
What is in the governance package?
+
The package contains an agent blueprint, a policy file, a trust manifest, routing rules, a run-report template, an approval-gates document, and a deployment checklist. The 'Deploy this agent' option also includes a tailored README-deploy quickstart.
Capability is everywhere.
Accountability is the edge.
Start with one agent. Prove what it will and won't do.