HN Showcase
Back to browse
Let your local agents trade on internal prediction markets

Let your local agents trade on internal prediction markets

by catpower·Apr 1, 2026·3 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidBold BetBig Brain

AI agents trading on internal prediction markets to surface hidden team knowledge.

Strengths
  • •Hooks into private context like uncommitted code and Slack DMs that official trackers miss
  • •No email or login required for sandbox API access—frictionless testing for developers
Weaknesses
  • •Prediction markets for teams is known concept—needs proof AI angle adds real value
  • •Demo is 30 seconds—unclear if agents actually outperform human forecasters at scale
Category
AI/ML
Target Audience

Engineering teams at larger companies

Similar To

Metaculus · Augur · Polymarket

Post Description

I work at the N in FAANG. Forecasting and status updates are broken by politics and org structure. There’s always someone who already knows an A/B is not going to test well or a migration is behind yet that never makes it to the official tracker.

That knowledge exists but it’s in uncommitted code, one off SQL queries and private Slack DMs.

So I built an MCP that hooks up to a prediction market at https://implicitmarkets.com. Information aggregation meets AI reasoning over private context.

Here is a 30-second demo of a local agent reading commits, slack messages and making a trade. https://www.implicitmarkets.com/demo.svg

To see for yourself, I spun up a sandbox with some public markets. Grab an API key (no email/login) at https://implicitmarkets.com/developers, connect your own pet Claude via the MCP and see if your agent can out AI the other AIs (and humans!).

Similar Projects

Finance●Mid

I gave my AI agent $50 and let it trade on Kalshi

The aggregator idea — scanning top-performing bettors for convergence signals and using an Adaptive Risk Stabilizer (ARS) to size tiny multi-parlays — is a neat, scrappy approach to "signal fusion" for micropredictions. It's fun and educational as a showcase of AgentWallet governance, but right now it's light on verifiable backtests, audit logs, and strict fail‑safes, so treat it as an experiment not a money manager.

Niche GemBold Bet
JackDavis720
203mo ago