AI Context

Bkper provides structured, machine-readable access to its entire site and documentation so that AI tools can understand the platform and help you use or build with it. Domain knowledge is exposed as composable, independent URLs — load exactly what a given agent needs, nothing more. Skills, AGENTS.md, custom agents, raw HTTP — the content works the same way regardless of how you access it.

Discoverability

Bkper implements the llms.txt standard:

• /llms.txt — site-wide index listing all sections with .md links, covering marketing pages, apps, company context, legal, and full documentation.

The file provides a high-level overview of the entire site. From there, AI agents can navigate to any article via section .md endpoints in at most two hops.

Page Access

Every page on bkper.com — marketing pages, documentation, and app listings — is available as clean Markdown. Navigation chrome (sidebar, header, footer) is stripped, significantly reducing token usage for AI tools.

.md suffix

Append .md to any page URL:

https://bkper.com/about              # HTML (browser)
https://bkper.com/about.md           # Markdown (AI tools)
https://bkper.com/docs/core-concepts.md

curl https://bkper.com/docs/core-concepts.md

Section .md

Section URLs return prose from the section index plus a listing of child articles and subsections:

curl https://bkper.com/docs.md           # Documentation root
curl https://bkper.com/docs/guides.md    # Guides section
curl https://bkper.com/apps.md           # Apps directory

This means an AI agent can navigate from /llms.txt to any article in at most two hops: root → section .md → article .md.

Starting points

Give your AI tool a section endpoint and let the conversation narrow from there:

• /docs/guides.md — user-facing guides
• /docs/build.md — developer docs
• /docs/api.md — all API libraries at a glance

Accept header

Request Markdown via content negotiation by including text/markdown in the Accept header. This works with the canonical page URL — no URL modification needed:

curl https://bkper.com/docs/core-concepts \
  -H "Accept: text/markdown"

The response includes an x-markdown-tokens header with the estimated token count, which agents can use to plan context window usage:

HTTP/2 200
content-type: text/markdown; charset=utf-8
vary: Accept
x-markdown-tokens: 1850

Curated Context

Three composable URLs expose the domain knowledge and behavioral guidance AI agents need when building on the platform:

URL	Purpose
/platform/agents.md	Technical instincts, quality standards, product sensibilities
/about/mission-principles-values.md	Mission, principles, values, and decision framework
/docs/core-concepts.md	Domain model — Books, Accounts, Transactions, Groups, Events

Each URL stands alone. Wire together whichever combination your project needs. For setup examples with specific tools, see Building with AI.

API References

API reference endpoints compile the library overview and full spec into a single compact document optimized for AI consumption:

• /docs/api/rest.md — endpoints, parameters, and data models
• /docs/api/bkper-js.md — bkper-js README + TypeScript definitions
• /docs/api/bkper-gs.md — bkper-gs README + TypeScript definitions
• /docs/api/bkper-api-types.md — shared TypeScript type definitions
• /docs/api/bkper-web-auth.md — OAuth browser SDK

Compiled Markdown vs raw source (overview + openapi.json or .d.ts):

Library	Raw (tokens)	.md (tokens)	Reduction
REST API	~38K	~9K	4×
bkper-js	~32K	~18K	1.8×
bkper-gs	~22K	~12K	1.9×
bkper-api-types	~12K	~5K	2.4×
bkper-web-auth	~2K	~2K	~1×

Page Options

Every documentation page and app detail page includes a Page Options dropdown in the right sidebar:

Copy the page as Markdown, open it directly in Claude or ChatGPT, or grab a ready-made prompt for any AI tool.