# Terry Miles

Terry Miles writes about applying AI to business data and workflows, with a focus on context engineering, procurement, and helping teams use their knowledge to make AI systems more useful.

- Profile: https://b2binfluencer.marketing/creators/terry-miles/
- LinkedIn: https://www.linkedin.com/in/terrylmiles
- LinkedIn followers: 1,256
- Topics: artificial-intelligence, ai-in-procurement
- Based on 11 dated posts, latest 2026-08-25

## Summary

Terry Miles is most useful for explaining how AI context, memory, and procurement decisions affect enterprise data and team workflows.

- Best for: Enterprise software brands adding AI features that need expert content, not a product pitch.
- Not for: Reach-driven paid sponsorship with impressions, follower growth, or broad procurement awareness targets.
- Check first: Confirm whether they accept sponsorships, request terms and audience data, and find a contact route.

### Takeaways

- Miles separates model memory into short-term, semantic, procedural, and episodic types for personalization.
- A context engineering and MCP diagram becomes a feature-release checklist and observability exercise.
- For procurement, start with a simple question but plan an ambitious data scope.

## Main ideas

- **Business context is the asset; the team should keep owning it**: Across all four posts, the recurring claim is that a company’s own knowledge—not the model—is what makes an AI system work. Miles treats expert guidance as another name for context, argues that reusable context from one initiative pays off in the next, and warns readers not to let AI manage their context for them. The memory post adds a security dimension: customer session context is confidential, and procedures from colleagues or agents are proprietary. Keeping control also means deciding what the model never holds. In the diagram post, shared understanding of context across product and systems colleagues is the payoff—a new full stack, as they call it.
- **Start with a simple question, but an ambitious data scope**: Miles’s adoption advice is deliberately asymmetric: narrow the question, widen the data. A simple question reaches value quickly and is easier to fund. But choosing one whose answers require many stores forces the harder architecture, security and access work up front, avoiding rework later. The aim is not the first answer, but a capability—and reusable context—built across the whole estate.
- **Treat model memory the way an instructional designer treats knowledge**: Miles distinguishes context engineering from model plumbing: it means presenting the right knowledge at the right time by curating the model’s memory for the task. They divide that memory into short-term, long-term semantic, long-term procedural and long-term episodic, then map the categories onto a familiar distinction between a concept to recognise and a procedure to carry out. The practical implications: short-term memory is a question of personalisation as much as time; short-term load can complicate long-term memory operations; and procedural knowledge lives in logic and algorithms, not in the prompt.
- **Turn other people’s diagrams into working instruments**: Miles rarely reports new findings. Instead, they turn someone else’s diagram or paper into an exercise a team can run: reorder elements chronologically into a value-stream checklist, attach them to services and traces, or use Wardley mapping to decide what to build, buy or partner. The aim is a shared vocabulary for systems, security and product teams before they argue about features. The teaching anchor belongs to the guest; the contribution is the application.
- **Checklists are the right format for feeding expert judgement to a model**: Reviewing a Scale AI paper, Miles argues that rubric-writing skills from education, business analysis and instructional design transfer directly to reinforcement learning, where human-authored inputs guide the model. They highlight two details: separating essential from non-essential attributes of success helps a model prioritise and judge how far to reason; and checklists are the clearest format for those inputs because they lay out the elements of a finished piece of work.

## Work to read

- [Context Engineering, MCP, and Observability: Turning an AI Diagram into a Systems Conversation](https://www.linkedin.com/posts/terrylmiles_contextengineering-mcp-observability-activity-7371235792901492736-JVP-)
- [Rubrics as Rewards: Why Checklists and Instructional Design Skills Matter for AI Guidance](https://www.linkedin.com/posts/terrylmiles_rubrics-as-rewards-reinforcement-learning-activity-7368666931127533570-KuAH)
- [Context Engineering and Memory Types: A Vocabulary for Personalization and Proprietary Knowledge](https://www.linkedin.com/posts/terrylmiles_contextengineering-rag-ai-activity-7354185733064044544-INf9)
- [AI in Procurement: Start with Simple Questions, Ambitious Data Scope](https://www.linkedin.com/posts/terrylmiles_the-role-of-ai-in-sourcing-and-procurement-activity-7353849593752678400-RF0T)

## Brand relationships

- **Scale AI** (mention)
- **Decoding ML** (mention)

## Partnerships

Terry Miles's four posts, covering July 23 to September 9, 2025, address how procurement teams, system architects, and instructional designers can apply AI to business data. They mention no sponsor policies, rate cards, media kits, platform specifications, or disclosed brand partnerships, and include no commercial offer or inquiry route. For a potential partnership, ask whether they accept sponsorships and request those materials and a contact route.

## Alternatives

- Joseph Paul: Choose Joseph Paul when the need is specifically to explain how to structure memory in an AI agent. In his post on agentic memory, he breaks the problem into eight layers, from working and episodic memory to entity and shared memory. The framework helps a technical audience see why treating memory as one component can leave an agent forgetting or confusing context—and gives a memory-platform company a clear way to explain its role.
- Amy Daali, PhD: Choose Amy Daali when the audience needs an accessible introduction to AI agents or to the idea that language models may need more than larger models and longer prompts. Her article on agents explains agents through familiar ideas—planning, tools, memory, and feedback—and frames them as systems that can act toward goals. Her world-models article contrasts predicting words with learning from a changing environment. These pieces suit an educational campaign aimed at readers who need the concepts before they can weigh architecture choices.
- Gaurav Bhattacharya: Choose Gaurav Bhattacharya when the need is to address AI in B2B go-to-market operations. In his post about the AI-driven outbound arms race, he argues that automating execution does not guarantee better pipeline: trust, positioning, and distribution still matter. His digital-worker post makes the operational case through a concrete coordination problem—people manually coordinating disconnected systems—and identifies orchestration, permissions, reliability, and oversight as deployment concerns. That perspective is a closer fit for revenue and operations teams than a campaign focused on memory or personalization in AI products.

---
AI-assisted summary of public posts. Audience demographics are not available. Engagement appears only where we checked recent posts. Method: https://b2binfluencer.marketing/methodology/