Call for Proposals: Agent harnesses & small models in production

Two years ago, it was prompt engineering, then context engineering, then the harness: the tools, permissions and sub-agents you build around the model. Then the loop. Now the graph, and state that has to survive a crash at step 40 of 60.

Each shift arrives with a wave of posts written by people selling a framework, and it takes about a year to find out which parts actually held. So: which of these abstractions are earning their keep, and which are ceremony?

Meanwhile more teams are training and serving their own small models — and not all of them sit inside an agent. Sometimes it’s to cut the bill, often it’s data that can’t leave the building. Is a tuned 8B good enough for your problem? How would you know?

If you’ve designed tools an agent could actually use, or wrestled a long-running job into surviving a crash — if you’ve fine-tuned a small model and measured what you gained and lost — if you’ve made inference cheap or fast enough to ship, or built the evals that told you any of it was working — we want to hear from you.

What we’re looking for

• Talks grounded in hands-on experience, not slides lifted from a launch post
• Honest takes: what worked, what didn’t, and what you’d do differently
• Any domain: dev tooling, healthcare, legal, financial services, regional languages, enterprise search — it doesn’t matter

Format: 30-minute talk + 10 minutes Q&A

You don’t need to be an ML researcher. If you’re an engineer, data scientist or technical founder who has shipped and operated something with models in the loop, your experience is exactly what this audience wants. First-time speakers welcome, editors will work with you on structure.

Timeline

• Submission deadline: 15 August 2026
• Notification of selection: 22 August 2026

How to submit

1. Submit your abstract. Your abstract should clearly describe:

   • the problem or topic being addressed,
   • why it is relevant,
   • who the session is intended for, and
   • the key takeaways attendees can expect.

2. Add a link to draft slides within 3–5 days - after submitting your abstract, add a link to the draft version of your slides within 3–5 days. Draft slides help editors better evaluate the structure, depth, and delivery of the session.
   Submissions without draft slides may not be reviewed or may experience delays in receiving feedback.

About the editorial team

Chaitanya Sangani - meet-up editor. Chaitanya is an independent AI consultant. He is a member of The Fifth Elephant community and has reviewed talks for the Pune edition, and at The Fifth Elephant 2026 Annual Conference.

Srix Sriramkumar - reviewer. Srix is makes engineering teams AI-native.. Srix is a member of The Fifth Elephant community and has reviewed submissions for the Enterprise AI in production meet-up, held in Bangalore in June.

Contact

• Email: info@hasgeek.com
• WhatsApp / Phone: 7676332020