# How I Built a Self-Verifying AI Agent with DynamoDB and ReAct Reasoning

> Source: <https://dev.to/bob_lee_2d29b22cee96eb65f/how-i-built-a-self-verifying-ai-agent-with-dynamodb-and-react-reasoning-6dp>
> Published: 2026-06-26 04:34:25+00:00

*Built for the #H0Hackathon — Hack the Zero Stack with Vercel v0 and AWS Databases*

Most AI pipelines follow a fixed script: input in, output out, nobody checks the work. For the H0 hackathon (Track 2: Monetizable B2B App), I built **ChemSpectra Agent** — an FTIR spectral analysis system where the AI verifies its own conclusions and self-corrects when evidence conflicts.

Instead of hardcoding which tools to call, the agent uses a ReAct loop with Qwen-3.7-Max function calling. The LLM autonomously selects from 5 tools — `identify_material`

(130K+ reference spectra), `explain_peaks`

, `assign_functional_groups`

, `match_library_topk`

, and `search_public_results`

. A material ID request might trigger two tools; a deformulation request triggers all three analytical tools. The LLM decides, not the developer.

After tools return results, `_detect_evidence_conflicts()`

compares outputs. If `identify_material`

says "PET" but `assign_functional_groups`

found no ester groups, that's a contradiction:

```
expected_groups = {
    "pet": ["ester", "c=o", "aromatic"],
    "nylon": ["amide", "n-h", "c=o"],
}
```

The agent estimates confidence from match scores, candidate score gaps, and functional group coverage. Below 0.75 confidence or any conflicts, a verification round fires automatically:

```
needs_verification = (
    confidence < 0.75 or len(conflicts) > 0
)
```

The agent gets told exactly what went wrong and calls additional tools to investigate. Post-verification confidence is logged, creating traces like `[0.62, 0.84]`

.

Every session persists to DynamoDB with 30-day TTL — tool call logs, confidence traces, synthesis, final report. But we went deeper than basic CRUD:

`gsi-created`

(partition: `ALL`

, sort: `created_at`

) replaces full-table scan with efficient time-ordered query; `gsi-material`

(partition: `top_match`

, sort: `created_at`

) enables "show me all PET analyses" aggregation`chemspectra-stats`

table tracks `total_analyses`

and `total_tools_called`

via DynamoDB `ADD`

operations, safe under concurrent requests`attribute_not_exists(session_id) OR step <> :confirmed`

to prevent concurrent overwrites of finalized reportsRegulated industries (pharma, forensics) require this audit trail. DynamoDB fits because the primary access is single-item by `session_id`

, the GSIs cover the two secondary patterns, and TTL handles cleanup automatically.

The loop runs 2-4 iterations in under 30 seconds. Self-repair for malformed LLM JSON has near-100% recovery. This turns "AI that gives answers" into "AI that checks its work" — essential when reports go into regulatory filings.

**Try it**: [chemspectra-agent-h0.vercel.app](https://chemspectra-agent-h0.vercel.app) | **Code**: [github.com/jxbaoxiaodong/chemspectra-agent-h0](https://github.com/jxbaoxiaodong/chemspectra-agent-h0)

*This article was written as part of my participation in the H0 AWS+Vercel Hackathon.*