# Context engineering: a service credit example | SourceX

Canonical: https://refer.sourcex.si/guides/concept-context-engineering
Last updated: 2026-11-04

Context engineering is choosing exactly what information an AI system sees when it does a task: the instructions, tools, documents and history that matter, and nothing that misleads. In an ordinary business workflow it is the judgment an experienced employee makes before deciding, such as pulling the version of a service credit policy that was in force on the date of an outage, not the version in force today. A decision record that names the documents used captures a correct context.

## What does context engineering mean in an ordinary business workflow?

It means assembling the right inputs for one decision. In a business, that is the same work an experienced employee does when they pull the right contract, the right price list and the right policy version before acting.

Anthropic, which builds AI models, describes context engineering as the strategies for curating and maintaining the best set of information during a model's work, including instructions, tools, external data and message history. It frames the goal as finding the smallest set of high-signal information that makes the desired outcome most likely. More is not better. A model handed every policy revision ever written is as likely to quote the wrong one as a new hire would be.

That is why ordinary decision records are interesting. When a company logged which document a person relied on, it recorded a correct context selection. Our companion guide on [context engineering and the documents behind a decision](/guides/context-engineering-enterprise-operational-data) covers a credit limit case where the decision date selects the policy. The case below adds a harder twist: one ticket carries three dates, and a contract clause decides which one counts. For the broader idea of keeping records together rather than as isolated files, see [how to identify useful workflow context](/guides/how-to-identify-useful-workflow-context-instead-of-isolated-files).

## One service credit, three dates (Illustrative)

The company is fictional: a 260-person managed IT services provider that owes customers service credits when an outage runs past a threshold in its service credit schedule. The schedule is a policy document kept in a versioned library.

- **Revision 3**, in force January 1 to May 31: outages over 4 hours earn a credit of 15% of the monthly fee.
- **Revision 4**, in force from June 1: the threshold drops to 2 hours, same 15%.
- **Master services agreement, clause 9.2**: the schedule in force on the date of the incident governs.

A customer paying $9,600 a month suffers a 3-hour outage on May 28. They request a credit on June 3. The service director decides on June 10.

| Record | What it says | System | Context role |
|---|---|---|---|
| Incident ticket | Outage May 28, 3 hours, root cause logged | Ticketing | Sets the incident date and duration |
| Credit request | Customer asks for an SLA credit, June 3 | Ticketing, linked to the incident | Starts the task |
| Clause 9.2 | Incident date selects the schedule | Contract repository | Tells the decider which date counts |
| Schedule revision 3 | 4-hour threshold | Document library, version history | The rule that applies |
| Schedule revision 4 | 2-hour threshold | Document library, current version | The rule that looks right but does not apply |
| Billing record | Monthly fee $9,600 | Billing system | Needed to compute any credit |
| Decision note | "Rev 3 applies per 9.2; 3h below threshold; no SLA credit. Goodwill credit $480 approved." | Ticketing, by service director | The outcome and its stated basis |

An assistant given only the current schedule would grant a credit of $1,440 (15% of $9,600) because 3 hours exceeds revision 4's threshold. An assistant given the clause and revision 3 reaches the director's answer: no contractual credit, plus a separate $480 goodwill gesture the director was authorized to make. The difference between those two answers is the whole point of context engineering, and the decision note is the evidence of which context was right.

The case also shows what to leave out. The request date and the decision date are both on the ticket and both fall under revision 4. Including them is fine; letting either one select the policy is the error. Good context is not only the right documents but the right reading of which detail governs.

## The fields that make the right context recoverable

The decision can be rebuilt later only if a few fields survived alongside the ticket.

| Field | Where it sits in the example | Why the example depends on it |
|---|---|---|
| Incident date and duration | Incident ticket | The facts the clause points to |
| Link between request and incident | Ticketing relation | Stops the request date being mistaken for the incident date |
| Governing clause reference | Contract repository, cited in the decision note | Tells a reviewer which date selects the policy |
| Policy version with effective dates | Document library version history | SharePoint, for example, keeps a version history from which earlier versions can be viewed and restored |
| Fee at the time of the incident | Billing record | Any credit is a share of this figure |
| Decision note naming the version used | Ticket comment by the service director | Records which context was chosen, in the decider's own words |
| Decider's authority | Role on the ticket or approval matrix | Shows the goodwill credit was within the director's limits |

A model reviewer working from a tool such as micro1's flow, which lets a reviewer inspect a run's steps, tool calls and output against a rubric, would need exactly this kind of answer key to judge whether an agent picked the right context.

## What the example shows, and what it cannot

- **Old versions may not survive.** Microsoft notes that a SharePoint library keeps up to a set maximum number of versions and deletes the oldest when that limit is reached. A policy revised often can lose the version a past decision relied on.
- **A decision note is not always written.** Here the director cited revision 3. Many decisions record only the outcome, leaving the context to be guessed.
- **One correct decision is not a rule.** The goodwill credit was a judgment call. A different director might have refused it, and both could be within policy.
- **Access is not context.** If the company lets AI assistants read its systems through the [Model Context Protocol](/resources/mcp/model-context-protocol), that gives access to documents, not a record of which ones were right for a past decision, and it is not a license.

## Who owns these records, and what stays unknown

For decision records like service credits, the owner is usually the COO or head of service delivery, with the CFO involved because credits touch revenue. Contracts sit with legal, and the document library with IT. Customer contracts may limit reuse of customer information, which is why rights review comes before any discussion of value.

Records only matter if the company can license them. Companies in the U.S., Canada and the EU qualify, as do companies in the UK, Australia, New Zealand, India, Singapore, South Africa, Latin America, the UAE and Saudi Arabia when at least 70% of the data is in English. The company also needs 50 or more full-time employees at peak (contractors excluded), documented operating history, rights to license the records, and an authorized contact.

What stays unknown until SourceX reviews it: how many decisions can be rebuilt with their full context, whether old versions survived, how personal and customer data will be handled, and whether any buyer wants this task type. Interest in context engineering across the industry does not mean every ticket archive qualifies. Partners never request exports, policy files or sample tickets. The owner can prepare with [questions to ask before licensing company data](/resources/questions-to-ask-before-licensing-company-data). [Customer support workflows](/data-types/customer-support-workflows) covers the wider category, and more concepts are in the [data types hub](/data-types).

## Go deeper on context engineering

- [Questions to ask a client about context engineering](/questions/does-context-engineering-data-qualify): a short discovery script for checking whether a company's decision records could qualify.
- [Record gaps that make context engineering hard to assess](/questions/context-engineering-evidence-gaps): a guide to the lost versions, missing decision notes and unlinked tickets that weaken these records.
- [Context engineering review packet](/resources/context-engineering-review-packet): a list of the metadata a company prepares before SourceX reviews its decisions and policy history.

## Next step

> **Refer a company. No cap on rewards.** Default reward on a company's first qualifying transaction: the greater of $50,000 plus 5% and 15% of Actual Supplier Payout, with no cap; further qualifying transactions first agreed within 12 months of the first Closing pay 15%. Eligibility and payment conditions apply, including the USD 100,000 Minimum Transaction, and a signed Schedule A or addendum can differ. A lead, meeting or signature alone does not trigger payment.

If the service or finance lead confirms dated policy versions and decision notes that cite them, [register as a partner](/register), check the company against [who qualifies](/who-qualifies), and read the [terms](/terms) before you make the introduction.

## Sources

- https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents
- https://www.micro1.ai/blog/introducing-flow
- https://support.microsoft.com/en-us/office/view-the-version-history-of-an-item-or-file-in-a-list-or-library-53262060-5092-424d-a50b-c798b0ec32b1
- https://support.microsoft.com/en-us/sharepoint/lists/documents-and-library/how-versioning-works-in-lists-and-libraries
- https://refer.sourcex.si/terms
