# 🏆 Start Here: Register & Get Aura Credits: Aura Agent Hackathon

**URL:** <https://community.neo4j.com/t/start-here-register-get-aura-credits-aura-agent-hackathon/77191>\
**Category:** Aura Agent Hackathon 2026\
**Created:** [April 13, 2026, 2:56pm UTC](https://community.neo4j.com/t/start-here-register-get-aura-credits-aura-agent-hackathon/77191 "2026-04-13T14:56:02Z")\
**Posts on this page:** 1\
**Showing post:** 81

<div class="post-metadata">

**Author:** ![joslat](https://sea1.discourse-cdn.com/flex021/user_avatar/community.neo4j.com/joslat/32/36594_2.png) [@joslat](https://community.neo4j.com/u/joslat)\
**Post date:** [June 6, 2026, 12:27pm UTC](https://community.neo4j.com/t/start-here-register-get-aura-credits-aura-agent-hackathon/77191/81 "2026-06-06T12:27:57Z")

</div>

# **MarketMind**

### **The news names one company. Who _else_ just moved — and who quietly won?**

A US export ban hit the chip sector. Every name went red. One went green. Nobody typed it.

The green node is **SMIC** — a Chinese foundry the _same sanction protects_. MarketMind flagged it the moment the news landed, and the next day it really closed up **+3.45%**. I never told it to hunt for a winner. The graph found one on its own.

That's the whole idea. A headline names one company; a curated dependency graph — suppliers, customers, partners, owners, rivals, and the standing sanctions sitting over all of them — works out everyone _else_ in the blast radius: how hard they're hit, along what path, and which way they move. It reasons about **exposure** , not price.

 ![01-shockwave-graph](https://us1.discourse-cdn.com/flex021/uploads/neo4jcommunity/original/3X/7/b/7bea8bfb0afb83557eab436710ea6183fa1f2463.jpeg)

## **What is MarketMind?**

A reasoning engine on a Neo4j graph, fronted by an Aura agent. You ask in plain English — _"what did the 2023 chip export controls do?"_ — and it finds the event, runs the cascade, shows the path (`NVIDIA → TSMC → …`, fading each hop), names the regime, and points at the non-obvious name the headline skipped. Every number it hands back is a tool query against the graph. It doesn't freestyle.

## **The graph**

Small on purpose — **104 companies, 257 dependency edges, 27 events** — and every edge hand-vetted. The point isn't size; it's one rule.

**Four** relationship types ever propagate company-to-company: `SUPPLIES_TO`, `COMPETES_WITH`, `OWNS`, `PARTNERS_WITH`. That's the cascade. **Everything else** — countries, commodities, themes, sanctions — only _seeds_ the shock at the right doorstep, then gets out of the way. It's never walked. (Let a `Sector` node into the path and every chipmaker becomes two hops from every other chipmaker, and the whole thing turns to soup. So I don't.)

 ![schema-diagram](https://us1.discourse-cdn.com/flex021/uploads/neo4jcommunity/original/3X/4/8/4841787ab1545fffa056332b5a0e20a9b6079f1e.png)

 ![Screenshot 2026-06-06 133530](https://us1.discourse-cdn.com/flex021/uploads/neo4jcommunity/original/3X/1/2/1291f96a837850ae555b594d70e34938413e65e8.png)

Two more pieces make SMIC turn green:

- **A standing `Condition` node.** A sanction isn't a one-off event — it's a state of the world that sits there until it's lifted. It `CONSTRAINS` companies with a _sign_: minus for the firms it hurts, plus for the domestic one it protects. Tighten it, and the graph re-prices the whole set — beneficiary included — with no new modelling.
- **Validation lives in the graph.** Every real next-day move is an `ImpactRecord` node (2,565 of them), so _"did this actually happen?"_ is a traversal, not a footnote.

## **The agent**

Seven tools, each doing one honest job.

 ![image](https://us1.discourse-cdn.com/flex021/uploads/neo4jcommunity/original/3X/f/d/fd22c98919914553f9b252512af2c9d50c0e65b4.png)  
Agent walkthrough video:

- Only usage (short): [https://youtu.be/9v3TOlErWVw?si=E8ijdtXalxpedH24](https://youtu.be/9v3TOlErWVw?si=E8ijdtXalxpedH24)
- Full walkthrough: [https://youtu.be/garN\_\_tbDcA?si=k-3slowOp8VSs4MZ](https://youtu.be/garN__tbDcA?si=k-3slowOp8VSs4MZ)

| you ask | it calls | you get |
| --- | --- | --- |
| "what did the 2023 chip controls do?" | `find_event` → `impact_cascade` | NVDA −0.66 · AMD −0.51 · TSMC −0.48 · … **SMIC +0.35 (up)** |
| "did that really happen?" | `validate_history` | NVDA −7.12% · **SMIC +3.45%** — misses kept in |
| "why is NVDA exposed?" | `company_dependency_map` | its suppliers, customers, rivals, owners |
| "what constrains SMIC?" | `active_conditions` | the export-control rule, and which way it cuts |
| "will NVDA go up tomorrow?" | — | it declines, politely |

The language model only names the company the news actually hit. The graph does everything past the headline.

 ![image](https://us1.discourse-cdn.com/flex021/uploads/neo4jcommunity/original/3X/1/7/179d470e4f15b97409f50e25ec1cc3a49449204e.png)

And another one, to follow up:

 ![image](https://us1.discourse-cdn.com/flex021/uploads/neo4jcommunity/original/3X/f/1/f168b0e4ff8d06e02d98afd22f6a91f8cb7020f2.png)

## **The honest part**

This is where most "AI + markets" demos promise you tomorrow's close. I won't — and the backtest is why. (If I could reliably call tomorrow's close, I'd be doing that for a living, not entering a hackathon.) Live data is the next experiment — and it'll face the same honest backtest before I claim a thing. We'll see what happens 🙃

On 27 held-out events, against real prices, next-day **direction** lands around **47%** — a coin flip. A dumb whole-sector average actually beats me on raw direction, 48.3% to 46.6%. I left that in the README; cropping it felt wrong.

What it _does_ do, measurably: it surfaces about **20% of the movers the headline never named** — which a headline-only reader catches **zero** of — and explains each with a path you can audit. The app overlays the real returns with ✓ and ✗, misses and all.

So: not a price oracle. A way to see who's in the blast radius and why, with the receipts. A sharp true claim beats a suspicious one.

 ![05-timemachine](https://us1.discourse-cdn.com/flex021/uploads/neo4jcommunity/original/3X/d/f/df68ac57e214398d9edfe63e33e9b1a0f3cb1b7e.jpeg)

## **There's an app, too**

Same graph, same engine, made cinematic. The news lands and a shockwave ripples out in red, fading by hop, SMIC green in the corner. Flip to a world map and the same shock arcs from Washington to Shanghai. Hit the Time Machine and the real next-day numbers drop in with their ✓/✗. Click any node for the per-hop math.

Note: I may have gotten a little carried away making this look like a trading-floor command center — but it's still genuinely useful under the hood. Still iterating; if you'd have built it differently, I'd love to hear how.

 ![04-map](https://us1.discourse-cdn.com/flex021/uploads/neo4jcommunity/original/3X/0/9/0965ef8fc62a3fc12e2489feea64937358ceefe7.jpeg)

App video — with the particle effects, because watching the shock actually ripple outward is half the point 😊: [https://youtu.be/2oStQKmEpBA?si=ffTew9XaNpMigvtc](https://youtu.be/2oStQKmEpBA?si=ffTew9XaNpMigvtc)

## **One footnote, kept honest**

The graph and all seven tools are **live and verified on Neo4j Aura** (Free tier) — everything above is real output from the running instance, driven from the Aura console.

Taking the agent _external_ — the public, shareable REST endpoint — is currently held up by an unresolved credit-redemption issue I'm still working through. _**(UPDATE - it is fixed, see the note below)**_ So rather than wait around, I run the same thing locally, two ways, both checked against the hosted agent:

- **the same graph in a local Neo4j (Docker).** Identical seed and records, where the same Cypher-Template tools return the same rows as the hosted agent — and a parity script confirms it agrees **to the sign, on every one of the 27 events.**
- **a local agent on Microsoft's Agent Framework** (with Azure OpenAI as the model). It does the same job: the model reads the headline and names the company; the cascade engine — in-process, and at parity with the Cypher — propagates it through the graph.

Same graph, same engine, same answers - but most probably much more latency... as the Aura Agent is native and co-located to the Aura db. The hosted endpoint only adds the public door; the moment the credit-redemption issue is sorted, it goes up with nothing else to change.

> ### _ **Update! - Now it works with the Aura Agent! I left the workaround under a flag - documented in the source code - see below so you can still play with it fully locally 🙂** _

> I have published the app as open source, as the issue with the credit redeeming is gone - thanks @Ari_Neo4j for the supper support and incredibly fast reaction time!!!
> 
> Check it out here: [GitHub - joslat/MarketMind: When news breaks, the damage travels. MarketMind traces it across a Neo4j company-dependency graph — who's hit, how hard, and the non-obvious name the headline never mentioned. Reasoning + exposure, not prediction. · GitHub](https://github.com/joslat/MarketMind) - and remember to star it!!
> 
> _**(it has all the necessary artifacts for you to recreate the graph database, seed the data, regenerate the golden dataset with the calibration needed and the Aura Agent)**_

---

_Built on Neo4j Aura, a directional cascade engine in three languages kept at parity, and an unreasonable amount of re-checking the numbers._

---

_[View the full topic](https://community.neo4j.com/t/start-here-register-get-aura-credits-aura-agent-hackathon/77191)._