Release — April 17, 2026. Every paid query on
/api/v1/query and
/api/chat now runs through the new agentic librarian flow. No client
changes required.TL;DR
Answers stay on-domain
Multi-hop questions no longer drift. Ask for an NBA Polymarket
market and you get NBA markets — not soccer, not baseball.
Full collections preserved
Comparison queries return the whole relevant set instead of a
cherry-picked top-N, so your model can reason over complete data.
Adaptive depth
Straightforward questions stay cheap. Broader comparison questions
can spend more work when needed. Buyers pay only for the depth
their question actually requires.
Honest capability misses
When the marketplace genuinely cannot answer, the runtime says so.
No synthetic numbers. No invented URLs. No confidently-wrong answer.
The story
Last month the system failed on one question that should have been trivial:“I want to make a 10k bet on something in the NBA Polymarket markets — what is an obvious bet with a decent return that I can make right now?”The old runtime returned soccer and baseball markets. Not because Polymarket didn’t have NBA markets — it did — but because the old runtime couldn’t recover from a bad first step. It planned once, executed once, and shipped whatever fell out. That query is the reason we rebuilt the execution layer.
What was broken
The old runtime treated every question as a single plan, single execution problem:- Bad first plans never self-corrected. If the first step landed on the wrong slice of the marketplace, the rest of the pipeline faithfully produced the wrong answer.
- Soft failures forced full restarts. One empty page from a paid tool could cost you a second full run.
- Coverage was lossy. Collection queries got cherry-picked top-N answers because the runtime preferred summarization over completeness.
What changed
The new runtime treats every query as a bounded, step-by-step conversation between the model and the marketplace:- At each step, the runtime checks whether the question’s scope is actually covered before deciding what to do next.
- If a tool returns the complete relevant collection, the whole collection is preserved through synthesis — no cherry-picking.
- If the first pass does not cover the question well, the runtime can recover before falling back to a partial answer.
- Collection questions preserve the relevant returned set through synthesis instead of collapsing prematurely.
Validation: before vs. after
Three queries from our regression suite, run post-migration against the live runtime on April 16:NBA — '10k bet on something with a decent return'
NBA — '10k bet on something with a decent return'
Before: answer drifted into soccer and baseball markets, ignoring
the explicit “NBA” constraint.After:
| Metric | Value |
|---|---|
| Outcome | answer — pass-with-caveats |
| Duration | 252s |
| Tool calls | 5 |
| Cost | $0.32 |
“As of April 16, 2026, the primary NBA markets on Polymarket with sufficient liquidity for a $10,000 bet are centered on long-term outcomes like the 2026 NBA Champion and Western Conference Champion. Among the active contracts, the San Antonio Spurs and Denver Nuggets represent the most liquid options…”The answer stays inside NBA/Polymarket, surfaces the liquid contracts, and explicitly flags that daily game lines weren’t part of the returned data instead of hallucinating them.
NBA Champion — 'best returns but highest probability'
NBA Champion — 'best returns but highest probability'
After:
The runtime returned the full 18-outcome collection and then
recommended Oklahoma City Thunder (43.5% implied probability,
$7M volume). The old flow would have cherry-picked a “top 5” and
lost the long tail.
| Metric | Value |
|---|---|
| Outcome | answer — pass-with-caveats |
| Duration | 86s |
| Tool calls | 2 |
| Cost | $0.12 |
BTC + news — mixed-intent query
BTC + news — mixed-intent query
After:
The runtime combined an on-chain exchange-flow tool with a news
search tool and produced a single grounded answer covering the
outflow data and the supporting news context. Six cents.
| Metric | Value |
|---|---|
| Outcome | answer — pass |
| Duration | 64s |
| Tool calls | 3 |
| Cost | $0.06 |
What this means for buyers
Per-response pricing is durable
A direct lookup answers in seconds for pennies. A deep comparative
question takes longer and costs more. You pay only for the path
your question actually required — not a flat subscription.
Pay for data, not for subscriptions
No $500/year lock-in to access Polymarket analysis, Coinglass
flow data, or news search. Your agent buys the response, pays in
USDC, and moves on.
Agents don't need KYC
Wallet-native payment means your agent can actually transact — no
credit-card form, no account provisioning, no human in the loop.
Grounded beats eloquent
The win isn’t “more polished prose.” It’s grounded live retrieval
vs. confident synthetic narration. See the comparison page for
side-by-side receipts.
What’s next
- Variance reduction. We’re tightening when the runtime decides coverage is complete so similar queries produce more predictable cost profiles.
- Smarter planning hints. The next pass uses more contributor metadata so efficient retrieval patterns are picked by default.
- Canonical payload retention. The full tool output is persisted and passed through to synthesis in the common case, so decorative fields like market URLs and source links survive end-to-end.