← Back
AWS ML Blog

Extending public sector intelligence with Agentforce and AWS

•15 min read•
#agents#deployment#mcp#bedrock#amazon
Level:Advanced
For:AI Engineers
✦TL;DR

This article details an end‑to‑end integration that combines Amazon Bedrock Data Automation with the Model Context Protocol (MCP) to turn unstructured evidence stored in Amazon S3 into structured insights that can be queried via a Salesforce Agentforce AI agent. The solution uses S3 event notifications to trigger a Lambda that registers the file in DynamoDB and starts a Bedrock Data Automation job; a second Lambda, triggered by EventBridge, writes the processed results back to S3 and makes them available through MCP via the Bedrock AgentCore Gateway. Engineers can now automate extraction of multimodal data (video, audio, scanned documents) and surface it in‑context within Agentforce without leaving the Salesforce console.

⚡ Key Takeaways

  • The workflow stores raw media in Amazon S3, then uses an S3 event notification to invoke an AWS Lambda function.
  • The first Lambda creates a document ID, writes metadata to Amazon DynamoDB, and launches an Amazon Bedrock Data Automation job.
  • Upon job completion, an Amazon EventBridge rule triggers a second Lambda that saves the structured output to a dedicated S3 bucket.
  • Agentforce queries the processed data through MCP; the request passes through Amazon Bedrock AgentCore Gateway to a Lambda‑hosted MCP server, which fetches results from DynamoDB and S3 and returns them to the agent’s context.
  • The integration leverages Amazon Bedrock AgentCore, which can work with any model or framework, to authenticate and route MCP calls.
💡 Why It Matters

By automating the extraction of actionable insights from large volumes of unstructured public‑sector evidence, teams can reduce manual review time and enable real‑time, natural‑language investigations directly within Salesforce, accelerating decision‑making and lowering operational costs.

✅ Practical Steps

  1. Configure the External Storage of Files with Amazon S3 connector in Agentforce Public Sector to route evidence files to an S3 bucket.
  2. Set up an S3 event notification that triggers a Lambda function to write file metadata to DynamoDB and start a Bedrock Data Automation job.
  3. Create an EventBridge rule that invokes a second Lambda to store the job’s structured output in a designated S3 bucket and ensure the Lambda serving the MCP server can query DynamoDB and retrieve results from S3.

Want the full story? Read the original article.

Read on AWS ML Blog ↗

More like this

Introducing workload recovery and expanded infrastructure checks on Amazon SageMaker HyperPod

AWS ML Blog•#deployment

Introducing Unity Gateway Insights

Databricks Blog•#deployment

Introducing Gemini 4 Neon

Google DeepMind•#llm

DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency

Hugging Face Blog•#llm

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING