Intermediate · 2 days
Building Enterprise AI Assistants
A two-day course for developers and platform teams: build a secure internal assistant that can use organisational knowledge and systems, with identity, permissions, citations and evaluation.
2 days · Intermediate · Architecture · Developers and enterprise platform teams
Overview
Internal assistants fail when they are treated as a chatbot with a company PDF attached. Enterprises need identity, permissions-aware retrieval, tool access to internal APIs, citations, logging and a deployment path that security will accept. This course is about that system.
You design and build an assistant architecture: enterprise search and RAG, identity and SSO, data access, tool use, workflows, conversational context and memory. Security, privacy, logging, evaluation and deployment are part of the same build, not a later hardening pass.
The practical work is an internal knowledge assistant that can answer from permitted documents, call a constrained internal tool, cite sources, and refuse when it should.
You leave with a working assistant and a clear list of the platform pieces — identity, retrieval ACLs, audit — that a product team should not have to reinvent.
Audience
Developers and enterprise platform teams building internal assistants, copilots or knowledge systems.
Prerequisites
Professional software development experience and familiarity with authentication concepts. RAG experience is helpful. Access to a representative document set improves the labs.
Duration
2 days
Can be delivered against your organisation’s identity provider, document stores and internal APIs.
Learning outcomes
- 01
Design an assistant architecture that separates conversation, retrieval, tools and identity.
- 02
Implement permissions-aware retrieval so answers cannot cite documents the user cannot access.
- 03
Integrate identity and SSO into assistant sessions, tools and audit logs.
- 04
Connect constrained internal APIs as tools with validation and least privilege.
- 05
Provide citations, conversational context and memory without leaking across users or tenants.
- 06
Evaluate assistant quality, groundedness and unsafe behaviour before deployment.
- 07
Deploy an internal assistant with logging, privacy controls and an operational boundary.
Outline
- 01
Assistant architecture
- Conversation, orchestration, retrieval, tools and policy as separate concerns.
- Enterprise search versus RAG, and when both are required.
- Identity, SSO and the assistant as a system acting on behalf of a user.
- Build: session-aware assistant skeleton with authenticated access.
- 02
Knowledge with permissions
- Ingestion, ACL metadata and retrieval that honours document permissions.
- Citations, refusal and the behaviour when search returns nothing the user may see.
- Conversational context versus durable memory; isolation between users.
- Build: permissions-aware retrieval over an internal corpus.
- 03
Tools, workflows and internal systems
- Internal APIs as tools: schemas, scopes, and not granting the model the user’s full rights by accident.
- Workflows that need confirmation: tickets, messages, records.
- Privacy, logging and the data that must not enter a model provider.
- Build: add a constrained internal tool with an approval path.
- 04
Evaluation and deployment
- Evaluation sets drawn from real internal questions.
- Security review: injection, logging, identity and tool scope.
- Deployment: environments, configuration, monitoring and support.
- Build: complete the internal knowledge assistant and run it against an evaluation set.
Practical work
You build an internal knowledge assistant over a representative corpus. The system authenticates, retrieves only permitted material, cites sources, can call one internal tool, and is evaluated against realistic internal questions.
Takeaways
- A working internal knowledge assistant
- Patterns for SSO, retrieval ACLs and tool scopes
- Citation, logging and evaluation templates
- A deployment and security checklist for internal assistants
Delivery
Cognitecta delivers private corporate training, on-site or as remote live training. Courses can be run as published, or adapted to your organisation’s stack, domain and experience level.
Instructor
Nicholas Johnson, AI architect and software engineer. He has a degree in Artificial Intelligence and around twenty years of professional technology training, including hundreds of courses for engineering teams and large organisations. About.
Related courses
2 days · Advanced
Production AI Architecture
A two-day architecture course for senior engineers and technical leaders: reference architectures, model gateways, RAG, agents, security, evaluation and the operational concerns that decide whether a system can leave the lab.
2 days · Advanced
Architecting Enterprise Generative AI
A two-day course for architects and senior technical leaders: design enterprise-scale AI capability as a platform, not as a sequence of isolated projects.