David MartinThe Director's Chair Back to portfolioPortfolio
Module 5 of 8 · The context gap

Give the crew the script.

AI agents give confident wrong answers when they cannot see your company's facts. This module shows you how to build a shared knowledge base they can rely on, one approved file at a time. No data team needed.

63 min5 lessons1 field exercise5 question check
The Director's ChairGive the crew the script
Production
The context gap
Director
You
Crew
AI
Take
01
Scene
05
Part
II
madebydavidmartin.comFree course
Before you start

By the end of this module you will be able to:

  1. Explain why agents give confident wrong answers, and what context engineering means.
  2. Name the five kinds of knowledge an agent needs, and how to test each.
  3. Build a first knowledge base in two weeks, starting from real questions.
  4. Keep it accurate with five habits, and check it is ready before go-live.
Companion · Guide 5 · two-page PDFGive the crew the script

This module follows the guide section by section. Keep it open as a one-page reference while you work.

Lesson 5.17 min

Why agents sound sure and still get it wrong

An agent that does not know your services, prices or policies fills the gaps with plausible guesses. It sounds sure of itself either way. The fix for most wrong answers is better context: approved facts the agent can find and trust.

Context engineering means deciding what the agent should know, writing it down once in plain files and keeping it current. Anthropic's engineering team uses the term for the discipline of choosing what information a model works from. You do not need a data team to start. You need an owner, a clear structure and a regular review.

Why it matters

In a June 2026 survey of 101 enterprises, 57% had traced an incorrect AI agent answer to missing or inconsistent business context. Only 25% had a governed context layer in production.

VentureBeat, VB Pulse survey, June 2026
Lesson 5.29 min

Five kinds of knowledge an agent needs

Every agent that speaks for your company needs the same five kinds of knowledge. Each comes with a simple test.

KindIncludesTest it
Company factsFactsServices, products, locations, history and approved figures.Every number has a source and a date.
Voice and styleVoiceTone, words to use and avoid, and strong examples.Ask it to rewrite a sample in house style.
LimitsLimitsWhat the agent must never claim, share or promise.Ask a question it should decline.
How work gets doneProcessSteps, templates and who approves what.Ask it to walk through a task step by step.
Where to lookSourcesAn index that routes each question to the right file.Ask which file the answer came from.
The ownerKnows which files are current, and who approves changes."What did the agent get wrong this week, and which file fixes it?"
Lesson 5.36 min

A pile of documents versus a knowledge base

The most common first attempt is to upload everything. It feels thorough. It gives the agent old and new versions side by side and no way to tell which one is right.

A pile of documentsA knowledge base
Every document uploaded at onceA small set of approved files to start
Old and new versions side by sideOne current version, dated
Long documents on many topicsOne topic per file, with a clear title
Anyone can change anythingNamed owners and defined permissions
Answers with no sourceAnswers that name the file they used
Key idea

Write it down once. Every agent benefits.

Lesson 5.410 min

Build the first version in two weeks

Start with the questions people ask most, not with every file you own.

  1. QuestionsList the 20 questions staff and clients ask most often.
  2. FilesWrite one short file per topic that answers them.
  3. IndexAdd an index that says which file covers what.
  4. TestAsk all 20 questions. Fix the file behind every miss.
  5. OwnGive each file an owner and a review date.

A workable rhythm over ten working days: two days to collect the questions, five days to write the files, one day for the index and two days to test, fix and assign owners. Plain text or Markdown files work well because people and AI can both read them.

A starter file, in outline
Title: Managed backup service
Owner: Service lead
Last reviewed: (date)

What it is: two or three plain sentences.
Who it is for: the client types it suits.
Approved figures: each with its source and date.
Never say: claims, promises or names that are off limits.
Related files: pricing, onboarding process.
Lesson 5.58 min

Keep it accurate, then connect

A knowledge base is accurate on the day you finish it. These five habits keep it that way. Count the ones in place. 0 to 1: start with the index and owners. 2 to 3: add a weekly error review. 4 to 5: open it to another team.

  1. Log wrong answers. Each miss points to a gap.Try it: keep a list of answers that missed.
  2. Fix the file. Correct the source, then retest.Try it: "Which file should have covered this?"
  3. Date everything. Old facts cause confident errors.Try it: add a last-reviewed date to each file.
  4. Name owners. Someone answers for each topic.Try it: assign an owner to every file.
  5. Keep limits current. New rules go in when they change.Try it: "What must the agent never say?"

Before go-live

  • Top questions are covered.
  • Every file has an owner.
  • Limits are written down.
  • Answers name their source.

Expand when

  • Test answers are consistently right. Add the next 20 questions.
  • Owners update without reminders. The routine is working.
  • People ask it first. It has earned trust.
  • Another team asks. Connect their agent to the same base.

Keep a person involved when

  • Answers go to clients. A person approves first.
  • Prices or numbers appear. Check them against the source.
  • Private data is nearby. Set who can read and who can write.
The director's standard · Module 5

Be fair and clear.

A knowledge base is a set of written rules: what is true, what is off limits and who decides. Writing them down is an act of fairness. Everyone, people and agents, works from the same facts, and nobody is caught out by a rule that lived only in someone's head.

Fair also means consistent. When a limit applies, it applies to every agent and every team the same way. When a file is wrong, you fix it in the open and say which answers it affected.

  • State your limits plainly in one file anyone can read.
  • Give every file a named owner, so questions go to a person, not a void.
  • When an answer was wrong, log it, fix the source and tell the people who relied on it.
From my work

A shared knowledge base behind every agent

I co-built a company's AI knowledge base and wrote its agent identity and tone-of-voice standard. It gives the company's AI agents and Claude projects one approved picture of the business, and each approved update strengthens every system connected to it.

Files
86 interlinked Markdown files, one topic each
Routing
Query routing points each question to the right file
Voice
A tone-of-voice standard every agent follows
Access
Defined permissions: some projects read, some write back approved updates
See the foundation section on my portfolio home page
Field exercise · about 12 min

Start your knowledge base

Draft the first pieces of your starter knowledge base. You can finish the files over the next two weeks.

Your answers are saved in this browser only.
Knowledge check · 5 questions

Check your understanding.

Q1In the June 2026 survey, what did 57% of enterprises trace a wrong agent answer to?
Q2Where should a first knowledge base start?
Q3What does the index do?
Q4An agent quotes an outdated price. Which habit fixes it at the source?
Q5Which of these is on the go-live checklist?
Score 4 of 5 to complete the module.
Wrap

Module 5 in four lines.

  1. Wrong answers usually come from missing context, not a weak model.
  2. Five kinds of knowledge: facts, voice, limits, process and sources.
  3. Start from the 20 questions people ask most. One topic per file, dated, with an owner.
  4. Agents draft, people decide. A person approves anything that goes to a client.
Your next step this week

List the 20 questions people ask your team most often. That list is the first day of the build.

Further reading on my site

Pass the knowledge check to complete this module.

If this course helps you or your team, I would love to hear about it.

Tell me what you are working on, and I will share what has worked for me.