<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Lawrance Reddy — AI for good work — built on Microsoft Foundry.</title><description>A Microsoft MVP&apos;s notes on building AI products that do real good — impact verification, bilingual government-services agents, and the Azure Foundry patterns behind them. Written from pilot sites in KwaZulu-Natal.</description><link>https://www.foundryfield.net</link><language>en-za</language><copyright>© 2026 Lawrance Reddy</copyright><item><title>From pilot to programme — an MVP&apos;s playbook for scaling a social-good AI project on Azure</title><link>https://www.foundryfield.net/articles/mvp-playbook-social-good-pilot</link><guid isPermaLink="true">https://www.foundryfield.net/articles/mvp-playbook-social-good-pilot</guid><description>Most impact pilots never graduate. Here&apos;s how I think about Azure credits, managed identity, Foundry, and the un-sexy operational scaffolding that lets a good idea survive contact with the real world.</description><pubDate>Mon, 30 Mar 2026 00:00:00 GMT</pubDate><category>MVP</category><category>Azure AI Foundry</category><category>Operations</category><category>Social good</category><category>Scaling</category><author>bytezn@gmail.com (Lawrance Reddy)</author></item><item><title>ConservAxion — verifying clean-energy and biodiversity impact with Azure AI Foundry</title><link>https://www.foundryfield.net/articles/conservaxion-verifying-impact-with-foundry</link><guid isPermaLink="true">https://www.foundryfield.net/articles/conservaxion-verifying-impact-with-foundry</guid><description>An Azure Foundry pilot for impact verification. Clean-energy and biodiversity outcomes, validated by AI, anchored in a tamper-evident audit trail, deployed in pilot households in KwaZulu-Natal.</description><pubDate>Wed, 25 Mar 2026 00:00:00 GMT</pubDate><category>Azure AI Foundry</category><category>Confidential Ledger</category><category>IoT Hub</category><category>Social good</category><category>Impact verification</category><author>bytezn@gmail.com (Lawrance Reddy)</author></item><item><title>Grounding agents in government policy — lessons from building Pfula</title><link>https://www.foundryfield.net/articles/grounding-agents-in-government-policy</link><guid isPermaLink="true">https://www.foundryfield.net/articles/grounding-agents-in-government-policy</guid><description>When your knowledge base is messy government documentation translated across languages, grounding is the whole product. A practical look at Foundry Agent Service tools, MCP, and the guardrails that keep a bilingual assistant honest.</description><pubDate>Sun, 22 Mar 2026 00:00:00 GMT</pubDate><category>Azure AI Foundry</category><category>Foundry Agent Service</category><category>MCP</category><category>Grounding</category><category>Multilingual</category><category>Social good</category><author>bytezn@gmail.com (Lawrance Reddy)</author></item><item><title>AI for the offline last mile — IoT Hub, edge validation, and Foundry grounding for rural pilots</title><link>https://www.foundryfield.net/articles/ai-for-the-offline-last-mile</link><guid isPermaLink="true">https://www.foundryfield.net/articles/ai-for-the-offline-last-mile</guid><description>Bandwidth is expensive, connectivity is intermittent, and the device is probably a cheap phone. Here&apos;s the Azure pattern we use to run impact-verification agents on the edges of the network.</description><pubDate>Fri, 20 Mar 2026 00:00:00 GMT</pubDate><category>Azure IoT Hub</category><category>Azure AI Foundry</category><category>Edge</category><category>Rural deployment</category><category>Social good</category><author>bytezn@gmail.com (Lawrance Reddy)</author></item><item><title>Pfula — an isiZulu AI assistant for South African government services on Azure AI Foundry</title><link>https://www.foundryfield.net/articles/pfula-isizulu-assistant-on-foundry</link><guid isPermaLink="true">https://www.foundryfield.net/articles/pfula-isizulu-assistant-on-foundry</guid><description>A bilingual (isiZulu / English) government-services assistant built on Azure OpenAI and Foundry Agent Service — where the knowledge base is the tool-set and citizen-facing streaming is first-class.</description><pubDate>Sun, 15 Mar 2026 00:00:00 GMT</pubDate><category>Azure AI Foundry</category><category>Foundry Agent Service</category><category>Azure OpenAI</category><category>isiZulu</category><category>Social good</category><category>Government services</category><author>bytezn@gmail.com (Lawrance Reddy)</author></item><item><title>Verifiable impact — making green claims auditable with Azure Confidential Ledger</title><link>https://www.foundryfield.net/articles/verifiable-impact-with-confidential-ledger</link><guid isPermaLink="true">https://www.foundryfield.net/articles/verifiable-impact-with-confidential-ledger</guid><description>Carbon credits and biodiversity offsets only work if someone else can check the evidence later. A pattern for anchoring AI-generated verifications in a tamper-evident ledger.</description><pubDate>Sun, 15 Feb 2026 00:00:00 GMT</pubDate><category>Azure Confidential Ledger</category><category>Azure AI Foundry</category><category>Impact verification</category><category>Tamper evidence</category><category>Social good</category><author>bytezn@gmail.com (Lawrance Reddy)</author></item></channel></rss>