Engagement Overview
Squid, available at asksquid.ai, combines visitor identification, website analytics, and developer data services. Tactical Edge helped build its AWS-native generative AI engine: the data-indexing backbone that makes the platform's information usable for contextual retrieval and visitor intelligence.
The Challenge
- Bring the platform's data into an index that supports generative AI workflows.
- Connect indexed information with the visitor-identification product's context and interfaces.
- Build an AWS-native engine that can support product workflows as the data and use cases grow.
The Approach
- Build the generative AI engine on AWS and connect it to the platform's data.
- Index data so the product can retrieve relevant context for AI-assisted interpretation.
- Integrate that engine as a backbone of the visitor-identification and intelligence platform.
What Changed
The engagement delivered an AWS-native generative AI and data-indexing foundation behind Squid's visitor-intelligence product, rather than a standalone reporting assistant.
Build on This with AWS
For organizations facing similar challenges, Tactical Edge can connect Amazon Bedrock and AgentCore to turn trusted information into useful answers and actions.
An account team could ask why an account's activity changed. An agent could retrieve permitted journey events, summarize the observed behavior, and prepare a CRM follow-up task for review without treating inferred intent as an established fact.
| Service | How it helps |
|---|---|
| Amazon Bedrock | Summarize permitted visitor journeys and explain the observed signals behind a proposed follow-up. |
| Bedrock Knowledge Bases | Build on the engine's indexed data with permission-aware retrieval of account context and relevant platform records. |
| AgentCore Runtime and Gateway | Look up an account and prepare an approved CRM task using tenant-scoped tools. |
| AWS workflow services | Use Kinesis for incoming signals, Lambda for event processing, and a durable workflow for deduplication, retries, and CRM handoff. |
AgentCore connects agents to approved application tools and provides execution traces. Bedrock Knowledge Bases grounds answers in permitted source material, while Guardrails adds content and sensitive-information checks.
Tactical Edge maps these capabilities to the team's access rules, review steps, and operating requirements.
Built for Daily Operations
Visitor insights and CRM actions follow the product's consent, retention, tenant-isolation, and access rules. Teams review inferred buying signals alongside the underlying activity.
Track indexing freshness, retrieval relevance, grounded-answer quality, cost per useful insight, and the accuracy of downstream product or CRM actions.