PRIORI.SH what was knowable, when
HINDSIGHT IS ALWAYS 20/20.

Recreate what your agent could have known at any point in time.

Historical evals cheat when tools retrieve corrected present-day evidence. PRIORI.SH is the versioned evidence and environment layer: pin a past instant, retrieve only evidence knowable then, and replay the same state through Live, Replay, or a sealed Pack.

Live demo · no signup 13 sources · point-in-time vintages
AS OF —
Payrolls, trailing year · knowable then vs revised today
—
—
← drag to scrub →
PRIORI.SH API data · BLS nonfarm payrolls, ALFRED vintages

One evidence state across live tools, offline replay, and evaluation.

Systematic macro

Replay decisions on point-in-time data

Macro releases get revised; as-reported EPS gets restated. Pin every feature to its as_of vintage and a research agent or systematic macro backtest reads the release available on that date, not the value quietly revised in months later.

client.search(
  query="payrolls",
  as_of="2024-03-08",  # data available that day
  sources=["alfred"],
)
Agent

Test the agent against the corpus it actually had

RAG evals fail quietly when a June 2022 prompt can retrieve 2024 filings. Point your MCP client at PRIORI.SH with an as_of date and the agent only receives context that existed then — clean retrieval, cited facts, repeatable runs.

# MCP server
claude --mcp-server priorish \
  "As of 2023-05-31, what did the Fed signal
  about persistent inflation?"

PRIORI.SH does not grade agents or store traces. It supplies the evidence state those systems evaluate against. Building that state internally means continuously capturing source versions, normalizing them, sealing provenance, maintaining replay, and tracking every upstream source change.

A raw model — even one with web search — can't hand you a verifiable past. Pin the date instead.

The same prompt, the same model (Gemini 3.1 Pro), answered four ways. A raw LLM leaks whatever its training baked in. Give it web search and a strict point-in-time prompt and it can reconstruct famous numbers — but on anything that isn't front-page news it comes up empty, and it never hands you a vintage. PRIORI.SH grounds the answer in what was actually knowable — today, or on any past as_of — with the release date attached. Revisions move the truth; watch the answer move with it.

PROMPT —
Don't take our word for it — run it on your own agent.
Point any MCP client at api.priori.sh/mcp and give it the prompt. Same tools, your model. Sign up free for a key.

Gemini is a trademark of Google LLC. PRIORI.SH is not affiliated with or endorsed by Google; outputs are generated via the Gemini API and shown for illustration. See Terms.

POINT-IN-TIME GUARANTEE

Every response is filtered to what was knowable before it is returned — and every fact proves where it came from.

Each result is filtered to what was published at your as_of, then stamped with a provenance chain: a BLAKE3 content hash, the source filing, and a sealed extraction lock. Open any fact and trace it back to the original document.

13 sources, one timeline.

13 sources grouped by domain · click to expand
Filings & disclosures 2
Every version, every amendment.
EDGAR Earnings Calls
  • EDGARSEC: 10-K, 10-Q, 8-K, proxy, amendments.
  • Earnings CallsManagement commentary, Q&A, derived facts, and bounded source quotes.
Macro & central banks 9
Vintaged. The number that printed, not the latest revision.
ALFRED Fed SPF BIS IMF World Bank IDS WGI Pink Sheet
  • ALFREDFRED archival series — every release vintage.
  • FedFOMC statements, minutes, speeches, Beige Book.
  • SPFSurvey of Professional Forecasters vintages and expectations.
  • BISBank for International Settlements bulletins.
  • IMFWorld Economic Outlook, Article IV reports.
  • World BankWDI, country data, regional outlooks.
  • IDSInternational debt statistics.
  • WGIWorldwide Governance Indicators.
  • Pink SheetCommodity price series.
Markets & probabilities 2
Crowd consensus, dated.
Polymarket Kalshi
  • PolymarketDaily snapshots of crowd consensus.
  • KalshiRegulated markets on CPI, GDP, rates.
Need a source we don't cover yet? Email us.

Three lines from cold to first query.

REST
curl -G "https://api.priori.sh/observations/series" \
  -H "X-API-Key: $KEY" \
  --data-urlencode "metric=PAYEMS" \
  --data-urlencode "source=alfred" \
  --data-urlencode "as_of=2025-07-15T00:00:00Z"
Python
from priorish_sdk import PriorishClient

client = PriorishClient(api_key="...")
client.observation_series_by_key(
  "PAYEMS",
  source="alfred",
  as_of="2025-07-15T00:00:00Z",
)
MCP
# claude_desktop_config.json
{
  "mcpServers": {
    "priorish": {
      "url": "https://api.priori.sh/mcp",
      "headers": {
        "X-API-Key": "your-free-key"
      }
    }
  }
}

Try free today. Upgrade when the volume makes sense.

Demo No account Free
Shared pool. No signup. Structured search only.
Shared pool · Structured search
Open the demo →
Free Sign up $0
Personal API key, history, and natural-language queries.
  • Saved queries & history
  • Structured + natural-language
  • All supported sources
Create account →
Pro
For teams using Deep Research
$49 /mo
Billed monthly
Production API, SDK, and MCP access with included Deep Research credits.
Rate limit
5,000 / day
NL queries
60 / hour
API keys
5
Deep Research
18 credits / mo
  • Full series & saga history
  • Batch search (20 timestamps)
  • Document API & CSV export
  • MCP tool access
  • Deep Research credits included
  • Higher Pro tiers at checkout
  • Email support
Institutional · For desks & teams
For desks, asset managers, and platforms running PRIORI.SH at scale.
  • Bulk export
  • Full provenance pack
  • Custom retention
  • Priority SLA
  • Internal knowledge graphs on your data
  • On-prem / VPC
Custom
Let's talk
Talk to us →