The Harness Engineering Challenge: Fix the Agent, Not the Model | Hack Hour by Failproof AI
Picture: Magicball

Workshop In 3 weeks

December
Saturday
15:00–16:00 2026 · Bangalore time

The Harness Engineering Challenge Fix the Agent, Not the Model, Hack Hour by Failproof AI

Where
Not stated
Host
Magicball
Entry
Free
Sign-up
Apply, the host picks
Apply on Luma

All Bangalore events

You sign up with the host. foundercal only links to it.

Your event? Manage this listing Report a change

Who you meetThe people on the listing, and what the host tells us about the room.

  • Vikram Bhandari Host
  • Nivedit Jain Host
  • Nikita Agarwal Host
Investors Not stated The listing does not say
The format Hands-on, small group Workshop
Sign-up Apply, the host picks Free

AboutIn the host's words.

Part of Hack Summit 2026. See the full summit: https://magicball.dev/hack-summit-2026

Your agent works in the demo and fails in production. We have spent our time on why, and the fix is not a better prompt. We show our method, then you use it to raise a failing agent’s success rate with runtime policies only, on a live leaderboard that shows whose harness gains the most.

You’ll use: The Failproof CLI, a prepared challenge repo and one fixed model for everyone.

It skips a step, calls the wrong tool, loops, or declares success on a task it did not finish. Rewriting the prompt fixes one failure and breaks another, and a new model brings new failures. We treat reliability as a harness problem. We leave the model and prompt alone and write runtime policies that intercept tool calls to allow, deny or instruct the agent back on course. Each failure becomes a rule that survives prompt edits and model upgrades. This is backed by our research on runtime policies.

What we’ll do together

You start with a prepared agent, tasks it partly fails and a scoring script. The model and prompt files are locked, so you only change the policy file, then rerun the script. Your score is the pass rate across the tasks.

  • Set up and baseline. Clone the repo, run the agent and record your score.

  • Write the first policy with us. We take one failure as a group: read the trace, name the failure, write the policy, rerun.

  • Take the open challenge. Fix the remaining failures on your own and submit scores to the live leaderboard. Your policies may beat ours.

  • See the results. The top harnesses go on screen and the winners explain their best policy, so the whole room learns from the sharpest ones.

You leave with

  • A working policy file that runs with the Failproof CLI against the agents you already use.

  • A repeatable method: read the trace, name the failure, write the policy, verify the score.

  • The challenge repo, to rerun or adapt as a reliability benchmark for your own agent.

  • Your own before and after score, showing how much reliability you can gain at the harness layer without changing the prompt or model.

Who it’s for

Engineers who build or run LLM agents and have seen them fail in ways a prompt edit did not fix: AI, backend and platform engineers, and anyone responsible for an agent in production. You should be comfortable in a terminal and with git, and know how an agent calls tools. No machine learning experience is needed.

Before you arrive

  • Bring a laptop (macOS, Linux, or Windows with WSL) with a terminal, git and a code editor, and a GitHub account.

  • Install the Failproof CLI and the runtime the challenge repo needs, and clone the repo. If you can, run the baseline so the hour starts at the first failure. We email approved guests the links.

  • We provide the repo, scoring script, leaderboard and model access for the session, so you do not need your own paid API keys. No private data is needed.

After the session

  • The challenge repo stays public, the Failproof CLI keeps running on your own agents, and the leaderboard stays open after the summit for late submissions.

  • Our engineers are available afterwards to help you apply the method to your own agents.

About Hack Summit 2026

Magicball's Hack Summit is on Sat 12 Dec in HSR Layout, Bengaluru: 20 Hack Hours, 50+ booths and 1,000+ AI engineers in one building. Approval for this Hack Hour includes entry to Hack Summit 2026. Each Hack Hour has its own approval, so request a seat for every Hack Hour you want to join.

Hack Summit 2026 is in partnership with Grayscale Ventures and Testsigma.

See the full summit: https://magicball.dev/hack-summit-2026

More Hack Hours

Explore every Hack Hour: https://www.magicball.dev/hack-summit-2026#hack-hours

Full text on Luma .

Same week in Bangalore All 92 events

Dec
Sat 16:00
Meetup

Product-led Growth for Startups

Coffee with Founders Free
Dec
Sun 11:00
Dinner

AI Founders & Leaders Brunch

The AI Collective Free
Dec
Sun 16:00
Meetup

Off Campus

GrowthX Free
Dec
Mon 18:00
Pitch

Founder Pitches by CEDAT

Founders pitch

Samagata Foundation
Akash Akku
Dec
to 10 Dec
Conference

Great International AI Native Summit (GAINS) 2026

NIMHANS Convention Centre
Saltmarch Media
₹90 – ₹160
Dec
Wed 16:00
Pitch

AIBoomi Demo Room | BLR

Founders pitch

AIBoomi Free
Dec
Wed 18:00
Meetup

Startup Talks by CEDAT

Institute of Product Leadership | Executive MBA
Startup Foundry India
Dec
Wed 18:00
Dinner

Orbit by PeakXV and In-Space

Investors in the room

Peak XV Free
Dec
to 14 Dec
Conference

INDUS-Tech Expo 2026

Sector 12 Ground
Bengaluru Tech Summit 2026
Dec
Fri 18:00
Meetup

South Bengaluru Startups Meetup by CEDAT

Founders pitch

2ND FLOOR
Startup Foundry India
Apply on Luma Sat 12 Dec ↗