Stop Building Manual Quotes: Meet the Agentic Workflow for Kenyan Freelancers

Brian Koech — Tue, 17 Feb 2026 15:47:01 +0000

As developers, we hate repetitive CRUD work. Yet, every time we land a freelance gig, we spend an hour wrestling with Word docs or generic invoicing SaaS that doesn't understand M-Pesa or local business logic.

I’m excited to share how we're using Agentic AI at BetterQuotes to turn "billing" from a chore into a single prompt.
🤖 What is an "Agentic" Quote Agent?
Most invoicing tools are just "digital paper." You click, you type, you save.

An Agentic Agent is different. It doesn't just store data; it carries out an intent. It understands context, applies business rules, and executes multi-step workflows.

Inside BetterQuotes, the agent allows you to skip the menus. Instead of clicking "New Quote" -> "Add Client" -> "Add Item," you can interact with a system that:

Reasons through your request: "Create a quote for a 3-month React Native project for Safaricom, total 450k, split into 3 milestones."

Applies Logic: It automatically calculates the KES totals, formats the milestones, and attaches your branded header.

Closes the Loop: With one confirmation, it pushes the quote to the client and sets up the M-Pesa STK Push trigger for the deposit.

We built this with a "Dev-First" mindset:

Context-Aware: The agent remembers your common service rates and client preferences.

M-Pesa Integration (The Killer Feature): No more "Send me the screenshot" or manual reconciliation. The agent tracks the payment status via M-Pesa API in real-time.

Branding without the CSS: You get professional, high-fidelity PDFs and web-views without touching a design tool

The goal of BetterQuotes isn't just to "make quotes." It's to build a Business OS for the Kenyan ecosystem. Whether you’re a solo dev or running a small agency, you can now manage your team and your cash flow using a tool that feels as smart as the code you write

Standard-Bearer AI: Making Company Standards Conversational

Brian Koech — Tue, 27 Jan 2026 18:23:52 +0000

This is a submission for the Algolia Agent Studio Challenge: Consumer-Facing Conversational Experiences

Demo

What I Built

Project Link:
Live Demo: https://algosearch-alpha.vercel.app/
GitHub Repository: https://github.com/bryko254/algosearch

The Problem

🛡️
In my experience as a developer, I've seen internal coding standards buried in static PDFs, Confluence pages, or READMEs that nobody reads. This leads to "technical debt by accident"—developers want to follow the rules, but finding them is a chore. When information "foraging" is too hard, consistency dies

The Solution: Standard-Bearer AI

🤖
Standard-Bearer AI transforms stagnant documentation into a proactive architectural mentor. Built using Algolia Agent Studio, it allows developers to ask natural language questions and receive precise, company-sanctioned answers instantly.

Instead of browsing through a list of search links, the developer gets the exact answer extracted from the source of truth

How I Used Algolia Agent Studio

1. The Knowledge Base (Algolia Index)
I created a structured JSON index containing core standards for:

Python Style Guides (PEP 8)
Conventional Commits
Security & API Key Management
Database Migration Policies

2. The Brain (Agent Studio)
Using Algolia Agent Studio, I configured a "Standard-Bearer" agent. I implemented a strict System Prompt to ensure the AI acts as a "source of truth" guardian. It is instructed to only answer based on the indexed data, effectively eliminating hallucinations

3. The Experience (Frontend)
The frontend is a modern Vite application using InstantSearch.js. I integrated the new InstantSearch chat widget, which provides the conversational bridge to the Agent.

Auto-open Logic: The widget automatically greets the developer on load, reducing the friction to start a query.

Visual Cues: I added a custom mutation observer to show animated loading states while the AI is "thinking" and retrieving documentation

Why Fast Retrieval Matters

In a documentation context, latency is the enemy of adoption. If a developer has to wait 10 seconds for a search result or an AI response, they will simply stop using the tool and go back to guessing—or worse, following outdated patterns

**Reliable RAG (Retrieval-Augmented Generation): Fast retrieval allows the Agent to perform multiple lookups if necessary, ensuring that the AI’s response is always grounded in the most relevant, up-to-date documentation

Technical Architecture *🧠
*User Query: "How should I name my Python classes?"

Retrieval: Algolia searches the internal_documentation index for the "Python Style Guide" record.

Augmentation: The text "Use PascalCase for classes" is fed to the Agent.

Generation: The Agent Studio LLM synthesizes a helpful response: "According to our standards, you should use PascalCase for classes."

Team Members:
@brykoech254 Brian Koech

Forem: Brian Koech