MemoryBeta

Memory of every decision your team makes about its tests.

A durable, per-repository knowledge base your AI agent writes and the whole team reads. Quarantine calls, assertion conventions, maintenance TODOs, “always / never” constraints — captured once from your Ask AI conversations and respected on every future turn. No more re-litigating the same test decisions.

4memory categories
Autosaved + categorized
Teamshared, per repo
Memory · checkout-web · Beta

Quarantine login_oauth.spec — it's flaky in CI, revisit next sprint

Saved to repo memory · auto-categorized

Decision

Category

login_oauth

Linked test

Ask AI

Source

Active

Status

Decision
9
Insight
6
Maintenance
4
Context
3

Read on every future turn — by Ask AI, by the team in the Memory tab, and (Beta) by your AI agent over MCP.

How Memory works

The agent proposes — you approve — the whole team remembers

01

Decide in Ask AI

Work through a test decision in any repo-scoped Ask AI chat — quarantine a flaky spec, agree on an assertion convention, note a refactor.

02

Approve the save

When you agree, the agent proposes a memory. An Approve / Reject prompt appears above the composer — nothing is written until you confirm.

03

Remembered everywhere

It's saved, auto-categorized, and folded into the repo memory digest — read by Ask AI on every future turn, by the team, and by your agent over MCP.

Four kinds of memory

Every memory is auto-classified so the right context surfaces at the right time

Decision

Agreed verdicts — quarantine this spec, keep that assertion, delete the dead test. The calls your team has already made, so they aren't re-debated.

Insight

Observations and findings about the suite — what flakes, why a flow is slow, what a failure really meant. The hard-won knowledge that usually lives in one engineer's head.

Maintenance

Follow-up TODOs and refactoring notes — what to revisit, what to clean up, what's deferred until next sprint. Durable, not lost in a chat scrollback.

Context

Constraints and conventions — the “always / never / you have to know X before touching Y” rules. So neither a teammate nor an AI agent re-breaks them.

One memory, read everywhere

Written from your conversations, surfaced to every place your team works

Memory tab

Browse, search, edit, and archive every memory on the repo's Memory tab — with stale-test-spec warnings and a link back to the conversation that created it.

Ask AI

Every repo-scoped chat reads the memory digest first, so answers respect prior decisions instead of contradicting them.

CLI

Review and manage repo memory from the terminal with /memory in the TestRelic CLI.

Your AI agent · MCP

Cursor, Claude Code, and other agents read and write repo memory over MCP, so they code with your team's decisions in context. (Beta)

One memory, every surface reads it

Decisions captured once stay respected — by the next engineer, the next Ask AI turn, and your coding agent.

QA Engineer

Prompt

Should I re-enable login_oauth.spec?

Memory: quarantined last sprint (flaky in CI) — revisit after the OAuth redirect fix lands. No need to re-investigate.

Engineering Lead

Prompt

What test decisions has the team made on checkout-web?

9 decisions and 4 maintenance TODOs, surfaced from the Memory tab — each linked to the conversation that created it.

Developer (with AI agent)

Prompt

Fix the failing checkout test

The agent reads the repo memory digest first — and respects your quarantine and assertion conventions instead of proposing a contradictory fix.

Whole team

Prompt

Why is this assertion written this way?

A Context memory records the constraint ('never assert on toast timing') — so nobody, human or AI, re-breaks it.

Stop re-litigating your test decisions.

Memory is in Beta and included in the Growth plan. Start your 14-day free trial — no credit card required.

Not to be confused with Ask AI's conversation memory — Memory is per-repository, team-shared, and built from your test decisions.