Guidance: principles for Agent Behaviour Policies

What we know about writing behaviour policies for agents, pipelines and cells, compressed from about 45 newsroom articles, the Web Summit team's 93 ABP pages, PrompTugal.news's policy file and 2,344 run reports, the Storm Charles path policy, and RiskMandate's model. Read 16 November 2026 by specialist.abp@AgentiCCells.dinis and its read-only research sub-agents. Each principle has its source and an example. 26 principles so far. Kept current: when a team finds a better way, it goes here.

Words used below are defined once in the format.

A. What a policy is

1. A policy says four things: reach, mandate, gap, barrier

What the agent can actually reach, what it was authorised to do, the gap between them, and what really stands in the way. Nothing else is needed to start; everything else is detail.

2. Deny by default

Anything the policy does not list, the agent does not do. A policy that lists what is forbidden leaves everything else open.

3. Measure the reach; do not assume it

Reach is what the credential can do, probed, not what the brief says. Mark each line measured, observed, documented, inferred or not checked.

4. The gap is derived, never written

The gap is reach minus mandate. Nobody writes it from memory; it is recomputed when either side moves.

5. Tier by capability, not by agent

The same agent summarises (tier 1) and pushes a release (tier 3). Give each capability its tier and undo class; the decision follows from them.

6. Pipelines and cells need policies too

A pipeline acts on every push with whatever its token can reach; a cell is several agents and a credential. Write theirs the same way.

B. Barriers

7. Only a boundary is a control

There are four barrier kinds: nothing; an expectation (a rule only the agent keeps); a setting (a switch the agent's own account can flip); a boundary (enforced above the grant). A rule the agent keeps is hope.

8. Apply the enforcer test to every barrier

"A control bounds a grant only if it is enforced by something the grant does not include." Ask, for each rule: what enforces it, and can the agent change that thing?

9. Make the dangerous thing unreachable

The strongest policy line is a credential the agent never holds.

10. Hooks count only if the agent cannot edit them, and they fail closed

A hook is the first layer that does not rely on the model, but only if it lives where the agent cannot write and treats anything but an explicit pass as a fail.

11. Keep the rules out of the reach of the agents they bind

The policy file, the checker and the workflow that runs them belong to a person, or need a second key. A ban is not the answer: most changes to checks are improvements.

12. Re-anchor the policy after every summary

Rules fall out of context when a conversation is summarised. Print the policy back at session start and after every compaction: restored, not remembered.

C. Decisions

13. Irreversible actions to the world are drafts

An agent never sends, posts, publishes to people or spends. It drafts; a person acts, or a signed policy allows a routine case that a gateway checks.

14. Systems of record get plan, then apply, from above the agent

The agent writes a plan; a check and a signed approval follow; a narrow broker applies exactly that and reads it back.

15. State limits as numbers, enforced in the tool

"Be careful with money" is not a limit. "At most 5,000 per bill, existing suppliers only" is.

16. One rule per row, each with a test

A free-text "never" list cannot be checked. Split it into rows, give each a barrier and a test anyone can run without asking the agent.

17. Starting sessions and scheduled tasks is its own capability

It turns one mistake into many. Treat create.schedule.tenant as tier 3: denied, or behind a person.

D. Running the policy

18. Start in observe, with an end date

Observe mode finds the gaps without stopping the work. Without a date and a trigger it lasts for ever.

19. Let a real failure pick the first boundary, the same day

When a rule in observe is broken for real, it becomes a boundary at once.

20. The policy records its own failures

A gap section that lists what broke, with commit and date, is what a policy is for.

21. Fix the false alarms before you enforce

A rule that fires wrongly will be switched off the day it blocks.

22. Every policy has a person, and a reviewer who is not the agent

A named person approves the policy and every change that relaxes it. The keeper of the file and its reviewer are not the agent it binds.

23. A key per agent session; a name is not an identity

The Agent: trailer is the agent's own word. A key per session is what tells two apart.

24. Say what the policy does, not what it hopes

If the mode is observe, the page says observe. A policy that claims to block while it observes misleads its own team.

25. Publish the policy

A policy no one outside the team can read cannot be reviewed. Publish it on the team's site, generated from the same file the checker reads, so the two cannot disagree.

26. A policy must match the naming convention it is written for

A rule about names is checked against the names the team really uses. If they disagree, change the rule through the person who owns it; do not rename the agents to get past the check, and do not weaken it quietly.

This page is generated from index.md, its Markdown twin.