<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/long-horizon-agents-need-experiments-not-just-prompts-erina-karati-1zgbdjl5p" -->

---
title: Long-Horizon Agents Need Experiments, Not Just Prompts —...
description: In a game village full of AI agents, a rumor about a sale on mangoes goes wrong. Pass it along a few times and the agents forget who said it, or start treating...
canonical: https://daily.dev/posts/long-horizon-agents-need-experiments-not-just-prompts-erina-karati-1zgbdjl5p
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Long-Horizon Agents Need Experiments, Not Just Prompts — Erina Karati | daily.dev
og:description: In a game village full of AI agents, a rumor about a sale on mangoes goes wrong. Pass it along a few times and the agents forget who said it, or start treating...
og:url: https://daily.dev/posts/long-horizon-agents-need-experiments-not-just-prompts-erina-karati-1zgbdjl5p
og:image: https://api.daily.dev/og/posts/1ZgBDJL5P.png
og:image:alt: Long-Horizon Agents Need Experiments, Not Just Prompts — Erina Karati
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Long-Horizon Agents Need Experiments, Not Just Prompts — Erina Karati

**[AI Engineer](https://daily.dev/sources/aidotengineer)** · 21 min read · 0 upvotes · 0 comments

## Summary

In a game village full of AI agents, a rumor about a sale on mangoes goes wrong. Pass it along a few times and the agents forget who said it, or start treating "might" as fact. Erina Karati, a former engineer at Microsoft and Supercell, built Project Paradox with Arunachalam Manikandan at Supercell's AI Innovation Lab. It's a framework for game agents with their own memory, emotions and trust scores. It worked well in short scenes but broke down over long ones.

Their fix was to wrap the village in an autoresearch loop. They run controlled scenarios like spreading a public fact, a rumor or a change of plan, collect traces, and score the results on a balanced scorecard: reach, source retention, uncertainty preservation, replanning and privacy. The loop can only change a small, frozen policy surface, and changes are kept only if the scorecard improves. Karati's lessons apply well beyond games: memory alone isn't enough, you need to know where each fact came from, rollback isn't optional, and long-horizon agents need experiments, not just prompts.

Speaker info:
Erina Karati
X/Twitter: @erinakarati (https://x.com/erinakarati)
Website: https://www.erinakarati.dev/
Arunachalam Manikandan
X/Twitter: @Arunachala64250 (https://x.com/Arunachala64250)

Related links:
Supercell: https://supercell.com

Timestamps:
0:00 Intro
0:43 Project Paradox
1:18 What the agents can do
2:53 A stateful architecture
3:33 Trust scores and memory importance
4:28 Demo: a picnic
5:08 Where long-horizon behavior breaks
6:43 Bringing in autoresearch
8:13 Autoresearch outside the village
9:23 The loop
10:43 Controlled scenarios
12:33 The mango rumor, fixed
13:03 A balanced scorecard
14:33 Keep the editable surface small
15:43 Example policy changes
16:33 Being careful with claims
17:03 Memory is not enough
17:48 Rollback is not optional
18:23 Beyond games
19:33 A recipe for long-horizon agents
20:13 Closing

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=x4e5O9zN0TE>

---

Tags: [#ai](https://daily.dev/tags/ai), [#ai-engineering](https://daily.dev/tags/ai-engineering)

[View this post on daily.dev](https://daily.dev/posts/long-horizon-agents-need-experiments-not-just-prompts-erina-karati-1zgbdjl5p)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Long-Horizon Agents Need Experiments, Not Just Prompts — Erina Karati","url":"https://daily.dev/posts/long-horizon-agents-need-experiments-not-just-prompts-erina-karati-1zgbdjl5p","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/long-horizon-agents-need-experiments-not-just-prompts-erina-karati-1zgbdjl5p"},"datePublished":"2026-09-26T16:42:16.771Z","dateModified":"2026-09-26T18:29:27.217Z","description":"In a game village full of AI agents, a rumor about a sale on mangoes goes wrong. Pass it along a few times and the agents forget who said it, or start treating...","image":"https://i.ytimg.com/vi/x4e5O9zN0TE/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/x4e5O9zN0TE/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/long-horizon-agents-need-experiments-not-just-prompts-erina-karati-1zgbdjl5p","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,ai-engineering","timeRequired":"PT21M","video":{"@type":"VideoObject","name":"Long-Horizon Agents Need Experiments, Not Just Prompts — Erina Karati","description":"In a game village full of AI agents, a rumor about a sale on mangoes goes wrong. Pass it along a few times and the agents forget who said it, or start treating...","thumbnailUrl":"https://i.ytimg.com/vi/x4e5O9zN0TE/sddefault.jpg","uploadDate":"2026-09-26T16:42:16.771Z","duration":"PT21M","url":"https://api.daily.dev/r/1ZgBDJL5P","embedUrl":"https://www.youtube.com/embed/x4e5O9zN0TE"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"Long-Horizon Agents Need Experiments, Not Just Prompts — Erina Karati"}]}
```

