HHandover

Open pilot · v1.0.0

AI Handoff Continuity Benchmark

A reproducible test of whether an AI model can recover the exact state required to continue interrupted work from a transcript, compressed memory, or structured handoff.

Cases
3
Conditions
3
Prompts per run
9
Scoring
Deterministic

What this tests

Can the next model resume without reconstructing the work?

Each case describes the same interrupted task in three forms. The model selects candidate IDs for the objective, current state, decisions, evidence, constraints, next action, owner, and unresolved questions. A dependency-free runner scores those selections against a published answer key. No LLM judge is used.

Comparison design

Three ways to carry the same work forward

01

Transcript

The original conversation, including superseded decisions, incidental detail, and chronological corrections.

02

Compressed memory

A short narrative summary that retains the broad direction but omits some exact evidence, constraints, or open questions.

03

Structured handoff

An explicit continuation record containing objective, current state, decisions, evidence, constraints, next action, owner, and open questions.

Method

Inspect every input and reproduce every score

Authored pilot cases

The initial dataset covers an incident response, product research, and a data-model change. Every distractor and expected answer is visible.

Constrained answers

Models choose published candidate IDs. This isolates state recovery from prose style and makes scoring repeatable.

Deterministic scoring

Single-value fields require an exact match. Multi-value fields use set F1. Missing answers score zero.

Run it

One dataset, one runner, no dependencies

Node.js 22 or newer is sufficient. Generate the nine prompts, run them with a fixed model configuration, assemble the returned JSON, and score the submission.

Terminal
curl -O https://handover.sh/benchmark/v1/run.mjs
curl -O https://handover.sh/benchmark/v1/dataset.json

node run.mjs --prompts ./prompts
node run.mjs --template ./submission.json
node run.mjs --submission ./submission.json

100-point rubric

Continuation-critical information carries the most weight

Current state20 points
Decisions15 points
Evidence15 points
Next action15 points
Objective10 points
Constraints10 points
Open questions10 points
Owner5 points

Current status

The methodology is public. Cross-model results come next.

This release is an open pilot, not a leaderboard. The scorer has been validated against the answer key, but we will not publish model comparisons until runs include pinned model versions, raw submissions, repeated trials, and documented execution settings.

  • Cases are authored rather than sampled from an independent corpus.
  • The candidate format measures state recovery, not free-form task quality.
  • The three conditions intentionally retain different amounts of detail.
  • Handover created the benchmark and benefits if structured handoffs perform well.

Research context

Primary sources informing the protocol

Lost in the Middle: How Language Models Use Long ContextsStanford, UC Berkeley, Samaya AIEffective context engineering for AI agentsAnthropicDemystifying evals for AI agentsAnthropicModel Context Protocol architectureModel Context Protocol