First Token — production AI engineering, one Tuesday at a time

First Token is not another AI newsletter rounding up the week's headlines.

Every issue starts with a real failure mode, debug story, or architectural decision — drawn from production systems serving actual users. If it only works in a demo, it doesn't ship here.

One deep dive lands every Tuesday. Long enough to be useful, short enough to read on the commute.

Explore the archive About the writer

@ Written by Tekeshwar — Senior Software Engineer at xFarm. Previously: backend & AI systems at Breakthrough Apps.

Sample entry · 1 of 25

#09 / Retrieval High severity

Pure vector search, no hybrid.

Surfaces in: error codes · ticket IDs · SKUs · code symbols

Symptom

Vector search encodes meaning, not strings. "ENG-4823 deploy failure" gets encoded as "looks like a ticket ID about deploys" — returns semantically similar bugs, misses the exact ticket. Same failure hits every rare keyword: error codes, product names, version numbers.

Test

# 30 queries with exact-match content
# (IDs, error codes, SKUs).
# compare vector-only vs BM25 + vector (RRF).
# hybrid usually wins +5–15 pts recall@10
# on corpora with proper nouns.

Snippet

def rrf(rank_lists, k=60):
    scores = 
    for ranks in rank_lists:
        for rank, doc_id in enumerate(ranks):
            scores[doc_id] = scores.get(doc_id, 0) \
                + 1 / (k + rank + 1)
    return sorted(scores.items(),
                  key=lambda x: -x[1])

vec  = vector_search(query, k=50)
bm25 = bm25_search(query, k=50)
fused = rrf([[h.id for h in vec],
             [h.id for h in bm25]])[:20]

Fix

Hybrid by default. RRF is the simplest fusion — no tunable weights, robust to score-scale mismatches. Tradeoff: two indexes to maintain. Postgres pgvector + tsvector avoids the operational doubling in one store.

+ 24 more entries PDF · 25 pages

What you get

One deep dive every Tuesday

~1,800 words · one diagram

Backend-first · no prompt hot takes

01 / Production-grade

Tactics from real shipping, not blog posts about blog posts.

Every issue starts with a real failure mode, debug story, or architectural decision — drawn from systems serving actual users. If it works in a demo, it doesn't ship here.

02 / Backend-first

Written for engineers who ship the systems behind the demo.

APIs, queues, retrieval, caching, observability, evals. The boring infrastructure that makes LLM products actually work in production — not prompt engineering hot takes.

03 / One per week