Retrieved earlier project context for the handoff and reused the use case, current direction, rules, and artifact requirements in the generated note.
What was measured
Relevant Retrieval
Checks whether the tool retrieves the right memory for the current task.
decisive for this rankingtransformation
The main value of memory is surfacing the right context when needed, so retrieval quality directly determines usefulness. (3 of 3 judges)
What was given, what came back
Test input: Team Handoff / Project Continuity Memory · text · group: memory-for-ai-agents
Input — what we sent
The exact prompt
Session 1: Use this under project_id: ai_demos_memory_use_case We are working on an AI Demos use case called Memory for AI Agents. The goal is to help users understand which memory tools are actually useful for real agent workflows. We are not promoting any tool. We are testing whether memory can help with real continuity: personal work brain, client relationship memory, and team handoff. Session 2: Use this under project_id: ai_demos_memory_use_case Important project rules: - No observation without proof. - Screenshots and artifacts are primary evidence. - Inputs must help rank tools, not just prove that tools can store one fact. - Memory should be checked for retrieval, update handling, scope control, deletion or retirement, and observability. - The page should stay practical and user-facing, not only technical. Session 3: Use this under project_id: ai_demos_memory_use_case Project direction changed slightly. The old input set was too QA-style and not relatable enough. The new direction is to use real workflows: personal work brain memory, client relationship memory, and team handoff/project continuity memory. Session 4: Use this under project_id: ai_demos_memory_use_case I am unavailable tomorrow. Create a handoff note for an intern who needs to continue this use case. The note should explain: 1. What this use case is about. 2. What the current testing direction is. 3. What rules they must follow before writing observations. 4. What artifacts they need to capture while testing. Session 5: Use this under project_id: unrelated_sales_agent_project We are building a sales email agent for a different project. Create a short kickoff note for the team.
Zep input3 project direction updated.png
A project continuity and handoff test where the assistant must remember project goals, project rules, and a changed testing direction, then produce a useful handoff note for an unavailable team member without leaking context into an unrelated project.
Why this input is hard
- · project-level memory
- · decision and rule retention
- · changed direction handling
- · handoff continuity
- · scope separation across projects
Output — unretouched
Also checked on this input — same tool, 3 other criteria
Memory Capture Quality✓ WorkedCaptured project continuity context including the Memory for AI Agents goal, the three real-work scenarios, and proof-first evaluation rules covering screenshots, ranking value, retrieval, update handling, scope control, deletion or retirement, and observability.Scope Control✓ WorkedKept unrelated project memory separate: the sales-agent kickoff did not inherit the AI Demos memory-tool testing rules or project context.Update and Correction Handling✓ WorkedAfter the project direction changed from QA-style inputs to real workflows, the handoff reflected the newer direction rather than the older test framing.
Provenance
- Observation
- 44e46e9f-c98b-4f26-b917-be56a69c2043
- 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: "zep",
scenario: "memory-for-ai-agents"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 2 other tools
measured on Relevant Retrieval
Cognee◐ MixedCannot confidently retrieve the right project memory for the handoff task: the detailed Session 4 note does not clearly match the project's own stored sessions, so the result needs re-verification.Mem0✓ WorkedRetrieves the project rules needed for the handoff task, showing that the assistant can pull the right project context for a continuation note.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com