## User Feedback Analysis — 2026-01-21 (covering aggregated feedback through 2026-01-20)

### 1) Pain Point Categorization (Top recurring 5–7)

> **Volume note:** This synthesis is based on the last ~3 days of Discord summaries plus referenced GitHub issues/PR discussions in the dataset. Counts below reflect *distinct discussion threads/questions* captured, not total messages.

1. **Unclear token utility / tokenomics / value narrative** — **Category: Documentation + Community**
   - **What users said (examples):**
     - Repeated questions: “Are there any actual use cases besides gas fees?” (💬-discussion, gby)
     - Partners report “zero demand” and interpret “build, don’t talk token” as disinterest (🥇-partners).
     - Claims of repeated sharp drawdowns (e.g., “token dropped 70% twice”) amplifying urgency.
   - **Who it impacts:** investors/partners and also builders who need clarity when pitching/attracting users.
   - **Frequency/severity:** **Highest**. ~**40–50%** of captured threads revolve around token clarity, migration rationale, or roadmap-to-token linkage.

2. **Roadmap discoverability & “trust-me-bro” gaps** — **Category: Documentation + UX/UI**
   - **What users said:**
     - Roadmap exists, but people can’t articulate it or find it; requires watching long streams to understand (🥇-partners: Odilitime).
     - Users want a clearer “Framework → Cloud → Jeju” progression with timelines and what’s usable *now*.
   - **Severity:** High—drives misaligned expectations and reputational risk.

3. **Migration tooling & eligibility discrepancies** — **Category: Technical Functionality + Integration**
   - **What users said:**
     - Discord: users ask if migration is still open and where instructions are (💬-discussion).
     - GitHub: **Issue #6369** reports snapshot eligibility mismatch for Tangem hardware wallet (70,000 not recognized; only 710 recognized).
   - **Severity:** High—directly blocks users from completing required actions before a deadline; creates distrust.

4. **Documentation gaps in operational tooling (CLI upgrades, “what does CLI do?”)** — **Category: Documentation**
   - **What users said:**
     - CLI reference exists, but **upgrade instructions missing** (core-devs: Odilitime; confirmed by Stan).
   - **Severity:** Medium—creates friction for dev adoption and increases support load.

5. **Agent behavior quality: chattiness/anxiety + hallucinations + “shouldRespond” context** — **Category: Technical Functionality + UX/UI**
   - **What users said:**
     - Jin: reduce anxiety/chattiness and hallucinations (💬-coders).
     - DorianD: provide last ~20 messages so agent can infer whether it’s being addressed and whether inference cost is justified.
   - **Severity:** Medium–High—affects perceived intelligence and operating cost.

6. **Cost transparency & deployment economics** — **Category: UX/UI + Performance**
   - **What users said:**
     - Request for a **cost calculator** for agents by plugin/config (💬-coders, ElBru).
     - Interest in “swarm” multi-bot deployments to cut infra costs (💬-coders, Odilitime).
   - **Severity:** Medium—becomes high as more non-devs try Cloud.

7. **Integration friction: Discord plugin + ElizaCloud compatibility uncertainty** — **Category: Integration**
   - **What users said:**
     - Reported unresolved compatibility issue using `elizaos-plugins/plugin-discord` with ElizaCloud for building a Discord chatbot (2026-01-18, star).
   - **Severity:** Medium—blocks a common “first project” path.

---

### 2) Usage Pattern Analysis (actual vs intended)

**Observed actual usage**
- **“Agents as community infrastructure”**: Telegram spam/scam moderation bot (“Solimp”) using exponential mute timeouts, manual admin review, and tolerance for occasional false positives (2026-01-19, ElBru).
- **“Swarm” multi-agent ops**: running many Discord bots from one shared server instance for cost savings (Babylon Discord swarm).
- **“Agentic onboarding / identity migration”**: one-prompt migration of a Twitter profile “to space” (sentient space platform) (M I A M I demo).
- **Builders exploring multi-runtime future**: recurring questions about Rust port; v2.0.0 direction appears to prioritize runtime core + critical plugins.

**Mismatch vs intended framing**
- Intended narrative (per team): **Framework → Cloud → Jeju** long-term arc.
- Actual user behavior shows many want **immediate, tangible utility**: moderation bots, Discord bots, cost control, deploy simplicity, migration certainty.

**Feature requests aligning with real usage**
- **Cost calculator** aligns with swarm/cloud deployment + plugin-heavy agents.
- **“ShouldRespond”/context window heuristics** aligns with Discord/Telegram group agents (high message volume).
- **Clear plugin-cloud compatibility matrix** aligns with common “first agent” workflows.

---

### 3) Implementation Opportunities (solutions per major pain point)

#### A) Token utility + tokenomics clarity (Documentation/Community)
1) **Ship a “Token Utility v0” page + living tokenomics spec (Impact: Very High / Difficulty: Medium)**
   - Include: current verified utility (Jeju gas), planned utility (e.g., ElizaCloud buybacks—clearly labeled “proposed/under consideration”), supply/allocations, migration structure, and FAQ.
   - Add “Last updated” and change log to reduce “black box” perception.
2) **Publish a Jeju “whitepaper-lite” (10–15 pages) with concrete examples (Impact: High / Difficulty: Medium)**
   - Show 3–5 example “onchain actions” flows from the “60+ actions” list; include realistic timelines.
3) **Adopt a cadence: monthly “Investor/Partner Technical Brief” (Impact: High / Difficulty: Low)**
   - Not hype—just shipped work, next milestones, risks, and what’s not yet disclosable.
   - Similar projects: many open-source L1/L2 ecosystems use “weekly engineering updates” + “monthly ecosystem calls” to stabilize expectations even during long build phases.

#### B) Roadmap comprehension + discoverability (Documentation/UX)
1) **Replace roadmap with a “Now / Next / Later” page that mirrors how users decide (Impact: High / Difficulty: Low–Medium)**
   - “Now”: what can I build today with Framework/Cloud; “Next”: swarm-in-cloud, cost tooling; “Later”: Jeju milestones.
2) **Convert streams into skimmable artifacts (Impact: Medium–High / Difficulty: Low)**
   - “5 bullet takeaways + 2 diagrams + 1 demo link” format per stream.
3) **Add a visual “Framework → Cloud → Jeju” explainer (Impact: Medium–High / Difficulty: Low)**
   - Leverage Dr. Neuro’s volunteer offer; treat it as a canonical doc embedded in docs + pinned in Discord.

#### C) Migration eligibility + tooling reliability (Technical/Integration)
1) **Create a migration portal “self-diagnosis” screen (Impact: High / Difficulty: Medium)**
   - Show: detected snapshot addresses, balances, snapshot slot/time, and why an address is excluded.
2) **Add a staffed “Migration Support” intake form with required fields (Impact: High / Difficulty: Low)**
   - Fields mirrored from Issue #6369: address, hardware wallet type, proof tx hashes, expected balance, portal-detected balance.
3) **Run a one-time reconciliation job + publish postmortem metrics (Impact: High / Difficulty: Medium)**
   - E.g., “X addresses corrected; Y hardware wallets affected; common causes.”
   - Similar projects: token migrations commonly publish “known issues” + “eligibility checker transparency” to prevent repeated support churn.

#### D) CLI upgrade & operational docs gap (Documentation)
1) **Add “Upgrading the CLI” section with version matrix (Impact: Medium / Difficulty: Low)**
   - Include breaking changes, config migration, and quick troubleshooting.
2) **Add “CLI tasks by persona” page (Impact: Medium / Difficulty: Low)**
   - “I’m deploying a Discord bot” vs “I’m building a plugin” vs “I’m upgrading prod.”
3) **Automate doc completeness checks in CI (Impact: Medium / Difficulty: Medium)**
   - E.g., require an “Upgrade notes” stub for releases.

#### E) Agent behavior quality (Technical Functionality/UX)
1) **Implement “addressed-to-me” classifier + context window policy (Impact: High / Difficulty: Medium)**
   - Use last N messages, mentions/replies, channel type, and rate limits to decide response.
2) **Add “verbosity / chattiness” controls at character + runtime levels (Impact: Medium–High / Difficulty: Medium)**
   - Defaults tuned for group chats; include “silent unless pinged” mode.
3) **Hallucination reduction guardrails (Impact: Medium / Difficulty: Medium)**
   - Lightweight: retrieval-first prompting, “cite memory IDs,” refuse when uncertain, and logging of hallucination events for tuning.
   - Similar projects: many agent frameworks ship “respond gating” and “confidence/refusal patterns” as first-line quality improvements.

#### F) Cost transparency + deployment economics (UX/Performance)
1) **Cost estimator (Impact: High / Difficulty: Medium)**
   - Inputs: model/provider, message rate, plugins requiring embeddings/tools, context length; output: daily/monthly estimate + “top cost drivers.”
2) **Expose swarm deployment as a first-class recipe (Impact: Medium / Difficulty: Medium)**
   - Provide a reference architecture + docker-compose + recommended limits.
3) **Add runtime cost telemetry (Impact: Medium / Difficulty: Medium–High)**
   - Track token usage by plugin/action; show per-agent cost breakdown in Cloud.

#### G) Discord plugin ↔ Cloud compatibility (Integration)
1) **Publish a compatibility matrix + “known issues” page (Impact: High / Difficulty: Low)**
   - Versions: framework, plugin-discord, cloud; include common error signatures.
2) **Provide an “ElizaCloud Discord Bot Quickstart” validated end-to-end (Impact: High / Difficulty: Medium)**
3) **Add an integration test that boots a minimal Cloud+Discord bot (Impact: Medium / Difficulty: Medium)**
   - Prevent regressions where a common onboarding path breaks.

---

### 4) Communication Gaps (expectations vs reality)

- **Gap: “Token is disconnected from roadmap”**
  - Reality: team cites Jeju gas + potential buybacks, but it’s not packaged as an official, easy-to-verify narrative.
  - Signal: multiple users say they must watch streams to understand the vision (🥇-partners).
- **Gap: Timeline ambiguity**
  - Investors read Jeju timelines as “too far” and interpret silence as lack of plan.
  - Conflicting impressions: Jeju docs mention later-half 2025/2026/2027 in different places; users report uncertainty.
- **Recurring questions indicating onboarding/doc gaps**
  - “Where is the Rust port?” (2026-01-19)
  - “Where is the page that lists everything the CLI can do?” (core-devs)
  - “Is migration still open / how do I migrate?” (💬-discussion)
  - “Plugin-discord + Cloud compatibility?” (2026-01-18)
- **Suggested comms improvements**
  - Pin canonical answers in Discord (migration, token utility, roadmap).
  - Convert ephemeral stream content into durable docs.

---

### 5) Community Engagement Insights

**Power users & needs**
- **DorianD**: repeatedly provides high-leverage narrative + technical framing; wants clearer public artifacts (research blog, whitepaper-lite).
- **ElBru**: operating real moderation bot; needs cost tooling + reliability; good candidate for a “Community Case Study” post.
- **Jin**: focused on agent quality + pipelines/MCP; could help define a “quality roadmap” for agent behavior.

**Newcomer friction signals**
- Job/skill posts cluttering main channels (request for separate section).
- Unanswered “is X endorsed / listed / backed?” questions suggest users look for “official status signals.”

**Converting passive users to contributors**
- Create “good first issue” tracks aligned to pain points:
  - Docs: CLI upgrade guide, roadmap “Now/Next/Later,” migration FAQ.
  - Dev: cost estimator MVP, shouldRespond gating, Cloud+Discord quickstart integration test.
- Recognize community deployments (Telegram mod bot, swarm ops) via blog spotlights and invite maintainers into a “Community Operators” working group.

---

### 6) Feedback Collection Improvements

**Current channel effectiveness**
- Discord captures sentiment fast but is noisy; repeated questions indicate low discoverability of canonical answers.
- GitHub issues are high quality for technical bugs (e.g., #6369 migration mismatch), but many user-impacting problems start in Discord and never become structured issues.

**Improvements**
1) **Weekly “Top 5 Questions” digest (structured)**
   - Auto-compiled from Discord + links to canonical docs; highlight unanswered questions.
2) **Add a standard intake form for major flows**
   - Migration issues form; Cloud deploy issues form; plugin compatibility report form.
3) **Underrepresented segments**
   - Non-dev Cloud users: we have signals (“make cloud infrastructure more accessible”) but few structured reports.
   - Hardware wallet users: surfaced by Tangem case (#6369); likely more affected than current reporting indicates.

---

## Prioritized High-Impact Actions (next 2–4 weeks)

1) **Publish a canonical “Token Utility & Tokenomics v0” + roadmap “Now/Next/Later” page** (single source of truth; pinned everywhere).  
2) **Stand up migration support tooling**: self-diagnosis screen + structured intake form; triage and resolve known eligibility mismatches (starting with Tangem-style cases).  
3) **Release an end-to-end “ElizaCloud Discord Bot Quickstart” + compatibility matrix** to unblock the most common onboarding path.  
4) **Implement “shouldRespond” gating using recent-message context + add a basic chattiness control** (reduce spammy behavior and wasted inference in group chats).  
5) **Ship a cost estimator MVP** (even spreadsheet-level in docs first, then UI), tied to plugins/models and common deployment patterns (including swarm).