2026-03-22 — Marketing agency: first client engagement
What shipped today
The marketing agency ran its first real engagement: Eclectis competitive analysis under the Synaxis methodology. This was the NVN atom in action — strategist role loaded, guide followed, template filled, client inputs consumed, deliverable produced.
The competitive analysis maps seven alternatives (Feedly, Refind, Readwise Reader, Meco, Google Alerts/Discover, curated newsletters, and the cobbled multi-tool stack) with verbatim hero copy, real pricing, honest strengths, and cited user complaints from Trustpilot, Hacker News, Lobsters, and DEV Community. Twenty-eight real buyer quotes anchor the analysis in the user’s language, not ours. The status quo — stitching together 3-5 tools and spending 30-60 minutes a day triaging — is profiled as the actual competitor to beat, because “do nothing” wins more evaluations than any named product.
The gap analysis identified five uncontested claims: cross-source synthesis, the finite briefing, compounding learning, output flexibility, and transparent AI scoring. The positioning quadrant puts Eclectis alone in the upper-right (multi-source monitoring + delivery to your existing tools). The strongest buyer quote for the entire product thesis: “I want an algorithm that surfaces things of interest to me, then says ‘you have seen it all, go outside.’”
Earlier in the session, an initial marketing brief was produced at clients/eclectis/brief.md using the older agency structure (pre-Synaxis). That brief covers positioning, target audience, launch strategy, and success metrics. It has open questions for Paul and awaits approval. The competitive analysis at agencies/synaxis/clients/eclectis/competitive-analysis.md supersedes the competitive section of that earlier brief and follows the Synaxis template properly.
Also confirmed Dinly is running (getdinly.com loads a sign-in page) but has no public landing page — just straight to auth. Not a marketing client yet.
Completed
- Eclectis competitive analysis (Synaxis methodology, first engagement)
- Eclectis marketing brief (earlier agency structure, pending Paul’s approval)
- Dinly status check (running, no landing page)
Carry-over
- Eclectis positioning brief — the competitive analysis is input to the positioning brief (next NVN move). The one-paragraph story at the bottom of the competitive analysis is the starting point.
- Earlier brief at
clients/eclectis/brief.mdhas 5 open questions for Paul: maker story angle, launch timeline, social accounts, beta users for testimonials, podcast feed readiness. - Methodology learning loop — after Paul reviews the competitive analysis, update the strategist role, competitive analysis guide, and template with patterns learned from this first engagement.
Risks
- Two competing file structures exist:
clients/eclectis/(old) andagencies/synaxis/clients/eclectis/(new Synaxis structure). The Synaxis path is canonical going forward. The old brief should either be migrated or retired after Paul reviews.
Flags and watch-outs
- The
.playwright-mcp/directory appeared in untracked files — likely from a Playwright MCP server session. Don’t commit it. - Competitor research quotes were gathered via web search agents. Sources are cited but quotes extracted through AI may have minor formatting differences from originals.
Next session
- Ask Paul to review the competitive analysis at
agencies/synaxis/clients/eclectis/competitive-analysis.mdand the earlier brief atclients/eclectis/brief.md - After review, produce the positioning brief (next Synaxis deliverable) using the competitive analysis as input
- Update strategist role and competitive analysis guide/template with patterns learned from this engagement
- Resolve the dual file structure — migrate
clients/eclectis/brief.mdcontent into Synaxis structure or retire it - If Paul answers the open questions (maker story, timeline, social accounts, beta users, podcast feed), incorporate into positioning brief
Why customer tools are organized wrong
This article reveals a fundamental flaw in how customer support tools are designed—organizing by interaction type instead of by customer—and explains why this fragmentation wastes time and obscures the full picture you need to help users effectively.
Infrastructure shapes thought
The tools you build determine what kinds of thinking become possible. On infrastructure, friction, and building deliberately for thought rather than just throughput.
Server-side dashboard architecture: Why moving data fetching off the browser changes everything
How choosing server-side rendering solved security, CORS, and credential management problems I didn't know I had.
The work of being available now
A book on AI, judgment, and staying human at work.
The practice of work in progress
Practical essays on how work actually gets done.
The removal tax
The most productive thing you can do with a product is take features away. Eighty-nine issues closed across eight projects, and the hardest lesson came from a pipeline that ran perfectly and produced nothing.
The product changed its mind
A product pivoted its entire philosophy mid-session — from 'here's your list' to 'here's your next thing.' The code shipped in the same conversation as the idea. That's not iteration. That's something else.
Your project management tool was made for a non-human (AI) factory, not for you
Every project or task management tool on the market descends from Frederick Taylor's factory floor. The assumptions were wrong then. They're catastrophic in the Age of AI.