Skip to content

Glossary

The 21 terms this site uses, each in a sentence or two of plain English. Underlined terms on other pages link here.

Acting identity#

The account whose permissions the agent uses when the agent acts. The account might be the person’s own, a separate agent account, a shared connection someone else set up, or a service account. The acting account isn’t always the person chatting with the agent, so products should show which account acts.

Give every agent job one owner and one rulebookSee alsoDelegationApproval

Approval#

A person’s agreement to one specific proposal: these items, these changes, this account doing the work. An approval records a decision about what the person saw. An approval doesn’t give the agent permissions the agent lacked, and doesn’t cover things that changed after the review.

Show the exact change before it happensSee alsoProposalStale proposal

Capability#

A job the agent can do for a user, described as an outcome (“prepare a campaign for this segment”), not as a list of functions. A tool is one action the agent can call, like “pause campaign”; one capability may need several tools plus a review step and a result check. A good capability has one owning team, clear permissions, and a shared meaning of “done.”

Give every agent job one owner and one rulebookSee alsoMCPActing identity

Delegation#

Handing a piece of work to an agent while a person stays responsible for the result. Linear makes delegation concrete: an issue can have a human assignee and a separate agent delegate. The agent may act with someone else’s permissions or its own. Salesforce’s customer-facing agents run as a designated agent user, not as the customer.

Give every agent job one owner and one rulebookSee alsoActing identityHandoff

Durable run#

Agent work the product saves, so the work survives a closed tab, a restarted server, or a new device. Each run and each change inside the run has a stable ID, so people can come back later and see what’s done, pending, or uncertain.

Keep working after the tab closesSee alsoOperation IDRetry

Handoff#

Passing a conversation or job from the agent to a person or team. Announcing a handoff isn’t the same as someone receiving the work: the next person needs the work and enough context not to start over.

Keep working after the tab closesSee alsoResolutionReceipt

Harness#

The machinery around an AI model that lets the model act: context and objects, the acting identity and its permissions, the screens where people review a change, and the receipts, history, and undo. For a product agent, the product is most of the harness; the model is the engine inside it.

See alsoProduct agentActing identityReceipt

MCP#

Model Context Protocol: an open standard for connecting AI tools to other products. An outside AI app connects to a product’s MCP server, the part of the product that exposes the product’s actions, to discover and call those actions. MCP moves where a request starts; the product still decides what’s allowed and records what happened. A valid connection doesn’t mean every action is allowed.

Give every agent job one owner and one rulebookSee alsoCapabilityActing identity

Operation ID#

A stable identifier for one intended change, kept when the job is retried, resumed, or taken over. The ID lets the product ask “did this exact change happen?” instead of guessing.

Keep working after the tab closesSee alsoRetryDurable runReceipt

Product agent#

Daniel’s working definition: an AI agent built into a software product that uses the product’s context and capabilities to carry out work for users, within the product’s permissions and controls. The work can be a change, a draft, or an answer based on current product data.

See alsoHarnessCapabilityActing identity

Proposal#

The specific change the agent plans to make, shown for review before the change happens: which items, which fields, which values. A good proposal is saved with an ID and a version, so the approval and the actual run refer to the same thing.

Show the exact change before it happensSee alsoApprovalStale proposal

Receipt#

A record, produced by the system that made the change, of what actually happened: which items, the before and after values, the outcome, and the evidence. A receipt is different from the assistant saying “Done,” which is only a claim.

Leave a receipt, not just a chat messageSee alsoVerified outcomeOperation ID

Regression case#

A saved example of a past failure, with the starting state and the expected result, rerun whenever the agent changes so the same bug doesn’t come back. A regression case is one kind of eval: a check of the agent’s behavior against a defined expectation. A monitor flags suspect live runs; a grader (code, a person, or another AI model) decides pass or fail, and needs checking too. A fix is proven on held-out cases, kept aside and never used to build the fix.

Turn every bad run into a fix someone ownsSee alsoTraceVerified outcome

Resolution#

A support metric for conversations the agent is counted as having solved. Vendors define resolution differently: Intercom separates confirmed from assumed resolutions, and HubSpot sets resolution status 72 hours after the visitor’s last response. Deflection, a conversation handled without a person, can include customers who left without an answer. Before comparing two rates, check what each rate is divided by: the same 300 outcomes are 30% of 1,000 conversations or 50% of 600.

Measure cost per result that actually workedSee alsoVerified outcomeHandoff

Retry#

Trying a change again after the change seemed to fail. A retry is risky when the first attempt may have worked and only the reply was lost. Idempotency means repeating a request doesn’t repeat the effect: the destination recognizes the operation ID and returns the original result instead of making the change twice.

Keep working after the tab closesSee alsoOperation IDDurable run

Stale proposal#

A proposal whose facts changed after someone reviewed the proposal: a new item matches, a record was edited, or access was revoked. The product should refuse the stale proposal, report the conflict, or ask for a fresh review instead of running the proposal anyway.

Show the exact change before it happensSee alsoProposalApprovalVersion check

Standing instruction#

A rule that lets the agent act later without asking each time, like “every morning, prepare new dates for overdue draft tasks in this project.” A trigger, an event or a schedule, starts the work; an agent that starts work this way is a proactive agent. A good standing instruction names the trigger, scope, acting account, limits, and owner, and the product checks permission again when the rule fires.

Let the agent act alone only within written rulesSee alsoActing identityApproval

Trace#

A step-by-step record of how an agent handled one request: model calls, retrieved data, tool calls, and results. Each recorded step is a span. Traces show where things went wrong, like the model receiving the right campaign ID but pausing a different campaign.

Turn every bad run into a fix someone ownsSee alsoRegression caseReceipt

Undo#

A new action that tries to reverse an earlier action. Restoring a value is different from reversing the value’s effects, like a notification already sent. An honest undo says what the undo will change and leave behind, and skips records someone edited since. Stop and Cancel only halt further work: neither reverses changes already made, and a cancel request has an outcome of its own.

Be honest about what undo can undoSee alsoVersion checkReceipt

Verified outcome#

A result someone has checked against a clear definition of done, using the changed record, a receipt, or a review with a rubric. The site uses verified outcomes as the unit for measuring cost and success.

Measure cost per result that actually workedSee alsoReceiptResolution

Version check#

Comparing a record’s version number, not just the value, before changing the record. A date changed from Friday to Monday and back to Friday looks untouched by value, but the version shows someone edited the date.

Be honest about what undo can undoSee alsoStale proposalUndo