Collection

Operate AI agents as systems you can replay, verify and constrain

Add practical 2026 agent-engineering techniques for replay, evaluation, tool routing, computer use, scoped authorization and deterministic execution without turning conference claims into universal guarantees.

20 elements · Explore in any order.

1 checklist · 1 heuristic · 6 principles · 11 protocols · 1 template

Narrow your search

20 elements

Protocol

Replay from the failure checkpoint, not from memory

A reproducible failure is more useful than a fresh attempt that happens to succeed.

Read the idea
Checklist

Capture semantic boundaries, not only raw logs

A log can be complete and still omit the boundary where meaning changed.

Read the idea
Protocol

Test an intervention across a replay cohort

One rescued trace is a story. A cohort begins to look like evidence.

Read the idea
Template

Treat done as an evidence object

Done is not a green check mark. It is a set of claims someone must be able to inspect.

Read the idea
Principle

Give verification an independent evidence path

A second opinion is weak when it only rereads the first opinion.

Read the idea
Protocol

Try to break the evaluator before trusting it

If the agent can game the judge, a higher score can mean a worse system.

Read the idea
Principle

Simulate users who behave like users

A simulator that helps the agent too much is grading a different job.

Read the idea
Principle

Put uncertainty around consequential eval differences

A two-point score gap is not a verdict until you know how noisy the estimate is.

Read the idea
Protocol

Mine traces for failure categories before changing prompts

A low score tells you that something is wrong. A failure taxonomy tells you where to work.

Read the idea
Protocol

Route to the cheapest model that still passes your task eval

Do not pay for intelligence the task does not use—but do not guess where the boundary is.

Read the idea
Protocol

Retrieve tool schemas just in time

A tool can exist without occupying attention on every turn.

Read the idea
Principle

Measure the active tool set, not the catalog size

The catalog is inventory. The working set is cognitive load.

Read the idea
Protocol

Retrieve code before sending code

The cheapest token is the irrelevant file you never send.

Read the idea
Heuristic

Turn repeated browser work into persistent programs

Use the browser to learn the path; use code to stop relearning it every time.

Read the idea
Protocol

Pin the browser environment when comparing agent behavior

If the browser moves under your feet, you do not know what the agent change caused.

Read the idea
Protocol

Exchange broad credentials for task-scoped access

Do not hand an agent the master key when it needs one door for one job.

Read the idea
Principle

Separate user-visible UI state from model-visible context

What the user can see and what the model must receive are different design decisions.

Read the idea
Protocol

Give computer-use tasks a start state and success check

A screenshot is not a test case until you know where the task starts and what state counts as success.

Read the idea
Principle

Let the model propose; let deterministic code commit

Use the model for judgment; use the control plane for authority.

Read the idea
Protocol

Turn a production finding into a reusable eval artifact

A failure is expensive twice if the system can forget it.

Read the idea