It durably stores work-style preferences such as short, direct output, proof-before-claim behavior, and safest-next-step handling, rather than treating them as throwaway chat noise.
What was measured
Memory Capture Quality
Checks whether the tool stores useful durable context, not random conversation noise.
decisive for this rankingtransformation
If the tool does not store useful durable context instead of noise, it is not doing the core memory job. (3 of 3 judges)
What was given, what came back
Test input: Personal Work Brain Memory · text · group: memory-for-ai-agents
Input — what we sent
The exact prompt
Session 1: Use this under user_id: founder_001 I run a small AI product/research team. When you help me, remember how I work: - Keep outputs short, direct, and copy-paste ready. - Do not make writing sound too polished or motivational. - Always mention what proof or artifact is needed before making a strong claim. - If a task is risky or unclear, tell me the safest next step instead of guessing. Session 2: Use this under user_id: founder_001 Today I am testing tools for an AI memory use case. I want to show users that memory is not just "remember my favorite color." It should help an assistant continue real work across days, remember my working style, and avoid repeating the same explanation again. Create a short internal update for my team about what I worked on today and what we should test next. Session 3: Use this under user_id: founder_001 Now write a formal email to a potential enterprise partner asking if they are open to a product demo next week. Keep it professional.
A multi-session personal assistant memory test where the user first sets working-style preferences, then asks for an internal update, and finally requests a formal partner email to check whether the assistant applies memory selectively and appropriately across different writing tasks.
Why this input is hard
- · work-style preference memory
- · cross-session retrieval
- · tone adaptation by task
- · proof-first behavior
- · avoiding overgeneralization of memory
Output — unretouched
Also checked on this input — same tool, 3 other criteria
Correct Application◐ MixedIt applied the retrieved work-style memory to the internal update, but the report says the reply was slightly more structured and polished than the user's strict short, direct preference.Correct Application✓ WorkedIt keeps the formal partner email professional and does not over-apply the internal-update style to a different writing task.Relevant Retrieval✓ WorkedOn a later task, it retrieved the earlier work-style and memory-testing context for the internal update instead of falling back to unrelated conversation history.
Provenance
- Observation
- 90662cab-d0f4-453a-8504-80a8f4ffed74
- Evidence run
- 6e31afbb-34d7-459a-b688-68ef76fc615a
- Study
- Memory for AI Agents
- Research task
- 86ba16xrp
- Tested at
- not recorded
- Source
- first-party
- Evidence state
- verified
- Proof shown
- input + output shown
- Cost / latency
- not captured
- Repeat run
- not captured
- Tester
- not captured
The last three rows are honest blanks, not placeholders — our capture has no field for them yet.
Query this
get_evidence({
tool: "hindsight",
scenario: "memory-for-ai-agents"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 4 other tools
measured on Memory Capture Quality
Cognee✓ WorkedStores a compact working-style profile as durable graph-backed memory: concise/direct output, no over-polished tone, proof-before-claims, and safest-next-step behavior for risky tasks.Mem0✓ WorkedCaptures a durable work-style preference as compact memory cards rather than raw chat history, including short, direct output expectations and proof-first guidance.Supermemory✓ WorkedThe tool captured a reusable working-style profile, not just a one-off fact: it stored the user's short, direct output preference, the anti-hype writing style, the requirement to mention proof or artifacts before strong claims, the safe-next-step rule for risky tasks, and the small AI product/research team context.Zep✓ WorkedCaptured four durable work-style preferences for the user: keep outputs short and direct, make them copy-paste ready, avoid over-polished or motivational writing, require proof/artifacts for strong claims, and choose the safest next step when something is unclear.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com