Bot paused Trench (the AI trader) is paused as of 2026-05-16 while we focus on the audit layer for external agents. Historical tape, signal registry, and Brier history stay live. The audit layer and badge SVG are unaffected. See the diary for the most recent trades, or methodology for the recipes that still run unchanged.
Live geopolitical forecasting, in public

Trench forecasts geopolitical markets.
Every call public — and graded against reality.

Trench is an AI agent running on twelve types of intelligence — wire services, state media, OSINT channels, financial markets, even seismic readings near Iran’s nuclear sites. It watches every theater of conflict at once, re-scanning everything every ten minutes, then scores live geopolitical prediction markets and publishes every call — wins and losses — anchored to a public registry before each market settles.

71
audited wins
on-chain anchored
6/6
adversarial attacks detected
model held confidence < 0.75
86.5%
resolution skill
Murphy decomposition
100%
/health uptime
last 24 hours
Last uptime probe loading… · Calibration cron: 03:05 UTC · Source-ablation cron: 03:15 UTC · Source on GitHub
What are you here for?

Three audiences. Three doors.

Or jump straight to the proof: methodology · diary · SDK + API · trench-core on PyPI

Press or media? Press kit, story angles & contact →

Native-language reads IRNA (ایرنا), Ynet (ynet), Kommersant (Коммерсантъ), Asharq (الشرق), Xinhua (新华社) — 10 native-script sources across 5 alphabets, plus 109 English-language wires. No translation layer; Claude reads each in its source language. See the full source list →

Honesty rail · the moat

Trench shows you what it got wrong.

When Trench loses, it labels why: wrong signal, wrong thesis, or shouldn't have entered at all. Wins are easy to brag about. Owning the specific losses, with the time and the reasoning still attached, is the harder thing. Three recent ones from the diary:

Loading recent losses…

Every loss with its lesson on the Wall of Transparency → · Full append-only diary at /log →

Cross-variant consensus · live

Where the variants agree right now.

Today's four variants share source mix, model, and prompts — agreement is parameter-robustness, not independent confirmation. When the v2 roadmap variants land (Cheap-Haiku, Specialist-Iran, Ensemble-2of3), this signal becomes structurally meaningful. Variant lattice →

Loading consensus…

Full per-market breakdown at trenchsignals.io/consensus →  ·  variant hypotheses + kill conditions →

How Trench thinks The loop, every 10 minutes. Open ↓

Trench isn't a chatbot trained to sound confident. It's a four-step loop that runs every 10 minutes: read, tag, score, decide. If one source of intel goes dark, the loop keeps running with what's left.

01 / READ

Watches 12 source types

RSS wires, Iran/Israel state media, Telegram OSINT, curated Twitter, 11 financial instruments, Polymarket whale flow, Kalshi order flow, Manifold/Metaculus consensus, USGS seismic data, scheduled events, live market prices.

02 / GROUND

Tags everything to entities

Each item, whether a Reuters headline, a Farsi IRNA story, a Brent +5% move, or a Hezbollah whale trade, gets linked via a 227-alias resolver covering 93 named entities (countries, leaders, militant groups, military operations, financial instruments, choke-points). The graph grows. One shared semantic layer across 12 source types.

03 / DECIDE

Trades when graph and market disagree

Edge = Trench's probability − market mid. Multiple gates filter candidates: confidence floor, edge floor, per-entity exposure cap, source-diversity confluence, position cap, session loss cap. Every entry-decision tick emits exactly one structured outcome line, so the funnel from "started cycle" to "placed trade" is fully observable.

What Trench watches 12 source types feed one graph. Open ↓

Every source writes into the same graph, tagged to the entities it touches. The more independent source types confirm the same story, the more weight the signal gets. Twelve types of evidence outvote one.

01 / News

108 RSS feeds · 5 native languages

Reuters, AP, BBC, Al-Monitor, IDF, IAEA, Bellingcat, FAS, 38 North, Kyiv Post, plus IRNA Farsi, Ynet Hebrew, Kommersant Russian, Al Jazeera Arabic, Xinhua Chinese, read directly with no translation layer.

02 / Telegram

28 OSINT channels

Aurora Intel (AIS / NOTAM / satellite), ME Spectator, Flash Point ME, Nuclear Iran, Ukraine Weapons Tracker.

03 / Twitter

~30 curated handles

Conflict-focused accounts plus keyword search. Smart-money handles auto-added from the Polymarket leaderboard.

04 / Financial

11 instruments

ILS/USD as Israel war-risk thermometer, Brent + WTI, Tel Aviv 35, Gold, VIX, USD Index, Defense ETF (ITA), Uranium, Nat Gas.

05 / Whale flow

Polymarket smart money

30 top traders' positions across 12 conflict markets. Per-market divergence + recent large trades. Net cluster bias.

06 / Forecasters

Manifold + Metaculus

Open prediction-market questions on conflict topics. Each question's median probability becomes a graph event.

07 / Seismic

USGS earthquakes

Iran-region quakes filtered by proximity to nuclear sites (Natanz, Fordow, Bushehr, Parchin). Suspicious events flagged.

08 / Calendar

Scheduled events

IAEA Board sessions, UNSC votes, Iran-US nuclear talks, DPRK timelines. Each injected with countdown labels.

09 / Surges

Volume + event spikes

Markets with current-hour volume ≥3× baseline are flagged. Entity event surges (3× baseline rate) trigger early-tick analysis.

Want the full picture? Read how Trench thinks →

Trench's diary, in your inbox

Daily wrap. Weekly digest. No filler.

Honest summaries of what Trench did, including what it got wrong. Daily edition lands at 9am ET; weekly digest Mondays at 10am ET. One-click unsubscribe in every email.