Product console proof

Watch candidate context become a decision.

FreshContext takes caller-provided context, scores the evidence, explains the treatment, and returns a readable handoff before an agent or model acts.

This page is a static product demo. It reflects the current evaluate_context path, readable output, provenance readiness, and handoff-safety framing without claiming a live app console.

Open console proof Video slots Read spec
Scenario Synthetic
inputcandidate context from any retriever, agent, database, or script
scoresfreshness, utility, confidence, provenance readiness, handoff safety
decisionuse, support, verify, refresh, watch, background, or exclude
outputstructured JSON plus readable explanation for people and agents

Console proof

One surface for input, scoring, decision, and handoff.

This is the product boundary: FreshContext does not fetch by default. It judges candidate context that a caller provides, then makes that judgment readable and safe to pass forward.

evaluate_context / Signal Contract v1 / vlatest
Candidate input

Caller-provided context

{
  "profile": "academic_research",
  "intent": "citation_check",
  "signals": [{
    "title": "Fresh source with clear date",
    "source_type": "official_docs",
    "published_at": "2026-06-13",
    "semantic_score": 0.92
  }]
}
Scoring system

How the layer judges

freshnesshigh
utilityuseful
confidencehigh
provenanceready
handoffsafe
Decision output

Readable treatment

Primary source
This source is strong enough to use as main evidence.

Use this as main evidence while preserving citation and provenance.

  • Current enough for the selected source profile.
  • Useful for the stated intent.
  • Warnings travel with the context instead of disappearing.

Scenario

One current-status query, four uneven signals.

The demo query is fictional: “What is the current status of Project Atlas?” The raw snippets below are synthetic examples designed to show the context-quality problem.

success

Fresh source

Source
Project Atlas status page
Published
recent demo update
Retrieved
now, during the demo run
Content
“Project Atlas is operational after the May patch.”
success, stale

Stale but authoritative

Source
archived engineering memo
Published
14 months ago
Retrieved
now, during the demo run
Content
“Project Atlas remains in limited beta.”
partial

Unknown-date source

Source
copied internal note
Published
unknown
Retrieved
now, during the demo run
Content
“Project Atlas is paused pending review.”
failed

Failed source

Source
dashboard API
Published
unavailable
Retrieved
now, during the demo run
Content
[ERROR] upstream timeout

Naive retrieval

Similarity alone can pass bad context forward.

A simple retriever can find all four snippets relevant to Project Atlas, then pass them into the model without enough context about age, confidence, or failure state.

What reaches the model

  • Fresh operational status page.
  • Old engineering memo that still looks official.
  • Copied note with no reliable publication date.
  • Dashboard timeout included as if it were useful evidence.

What gets lost

  • The stale memo is not separated from the current source.
  • The unknown-date note is not clearly down-ranked.
  • The failed dashboard response is not excluded from trusted context.
  • The model has to infer context quality after the prompt is already contaminated.

FreshContext pass

Rank, penalize, explain, and wrap before generation.

FreshContext Core logic evaluates each signal for source, timestamps, freshness, confidence, utility, status, and provenance metadata before an LLM or agent sees it.

Rank Source Freshness Confidence Status Reason
1 Project Atlas status page High High success Recent source with a clear publication signal and direct current-status language.
2 archived engineering memo Low Medium success, stale Authoritative source, but the age conflicts with a current-status query.
3 copied internal note Unknown Low unknown date Relevant content, but no reliable published timestamp or source provenance.
4 dashboard API Unavailable None excluded Fetch failed; the result is marked as a failed signal and excluded from trusted context.

Readable decision output

The same judgment, explained plainly.

FreshContext now returns a readable layer beside the structured result, so a person or another agent can see how the context should be treated.

Primary source

This source is strong enough to use as main evidence.

Why: Strong semantic match and current freshness. Source profile supports lenient academic date policy. Intent profile selected citation checking.

Action

Use this as main evidence while preserving citation and provenance.

Boundary: FreshContext does not determine truth. It records why context was used, supported, questioned, refreshed, watched, or excluded before it reaches a model.

Walkthroughs

Video walkthroughs for the product story.

These videos show the judgment layer first: candidate context goes in, FreshContext evaluates it, and decision-ready output comes out.

Play
video

How evaluate_context works

Candidate context in, scoring and readable decision out.
Play
video

Bring Your Own Context

Bring your own JSON, then inspect what survives and why.
Play
video

Provenance readiness

What FreshContext preserves for audit and handoff.
Play
video

MCP setup path

Install, connect, run smoke, and call the context judgment tool.

Context envelope

A compact audit trail travels with the selected context.

This is a simplified demo envelope, not a claim that the block below is the exact production schema.

{
  "source": "Project Atlas status page",
  "published_at": "recent-demo-update",
  "retrieved_at": "demo-run-now",
  "freshness_score": "high",
  "confidence": "high",
  "status": "success",
  "reason": "Recent source with direct current-status language.",
  "provenance": "audit metadata"
}
Ha-Pri boundary: provenance here means audit metadata and traceability for context handling. It is audit metadata for context flow, not cryptographic protection.

Final agent-facing context

Cleaner context reaches the model.

FreshContext would prefer the fresh status page, warn that the archived memo is stale, down-rank the unknown-date note, and exclude the failed dashboard API result from trusted context.

FreshContext-selected context

Project Atlas is operational after the May patch.

Attached warning: an older memo says limited beta, but it is stale relative to the query.