AI Literacy Adaptation Audit — Guinea-Bissau

DISCLAIMER — FICTIONAL RESEARCH DOCUMENT. This report is a speculative adaptation study produced as an example of what a structured market adaptation audit looks like when applied to AI literacy tool deployment in Guinea-Bissau. It was not commissioned by, requested by, or produced in collaboration with Anthropic, Claude, or Irreducibly Human. All case study profiles are fictional. All deployment recommendations are illustrative.

1. Country Context Summary

The single most important condition shaping Botspeak + Claude deployment in Guinea-Bissau is that the national lingua franca — Guinea-Bissau Kriol — is a Tier 0 NLP language with effectively no corpus, no production ASR, and no presence in FLORES-200, NLLB-200, or Masakhane benchmarks, while the official language Portuguese — for which full NLP exists — reaches only an estimated 15–25% of the intended user base, concentrated in urban Bissau.

Botspeak assumes the user can read the AI's output; in rural Oio, Tombali, Bafatá, and the Bijagós, functional literacy falls to 22–35%, and daily commerce, kinship, and governance run in Kriol or Balanta-Kriol code-switching. A text-first Portuguese Botspeak deployment is not a product for Guinea-Bissau; it is a product for a few thousand Bissau professionals who already have cheaper alternatives.

The primary risk if this condition is ignored:

The product will be confidently wrong in the field. Portuguese ASR does not fail silently on Kriol — it fails by returning plausible Portuguese sentences that mean something different from what the speaker said. A cashew aggregator dictating farmer payment records in Kriol will receive a Portuguese transcript that passes Botspeak's plausibility check visually but misreports village names, weights, and CFA amounts. In a market where the aggregator is the trust node for an entire farmer network, one wrong ledger destroys distribution for a season — and the cashew season only comes once a year.

2. Six-Dimension Matrix — Botspeak × Claude

Integrity Test Status

• ✓ Cashew Calendar applied — deployment timed to Nov–Feb build, Feb activation, Mar–Jun peak
• ✓ Portuguese Trap checked — product explicitly scoped as Kriol-voice, not Portuguese-text
• ✓ Kriol NLP gap assessed — corpus collection named as Phase 0 prerequisite
• ✓ AML/CFT enhanced flagged — relevant to any monetized or disbursement-linked deployment
• ✓ Political instability register — BCEAO named as anchor; ministry dependencies flagged
• ⚠ Payment idempotency — not applicable to pure literacy tool; flagged if bundled with cashew-payment workflow
• ✓ Aggregator network assessed as primary distribution channel
• ✓ Bijagós treated as distinct product universe (Case Study 2)
• ✓ Bijagó female authority mapped (Case Study 2)

3. Research Objectives

Objective 1 — Voice-First AI Collaboration Design

Viable interaction models. Inferred Given 15–22% mobile internet and 10–15% road paving, cloud-dependent native audio-to-audio models (Gemini Live class) are infeasible outside Bissau and Bafatá town centers for most of the year. The viable stack is a hybrid cascaded pipeline: (a) on-device Kriol wake-word and pre-recorded prompt scaffold; (b) opportunistic upload of audio when signal is available; (c) Claude generation server-side; (d) TTS read-back in Kriol via pre-recorded phoneme concatenation for a fixed vocabulary (numbers, village names, cashew weights, CFA amounts) plus Portuguese TTS for the formal-output layer. Observed cashew-season merchant logistics surge (Mar–Jun) materially improves interior 4G reach and is the only window where full cloud roundtrips are reliable in Oio/Bafatá.

ASR failure modes specific to Guinea-Bissau. Inferred from Portuguese ASR behavior on related creoles Portuguese Whisper and Azure models applied to Kriol exhibit:

1. Lexical substitution — Kriol bai ("go") → Portuguese vai, collapsing an aspect distinction
2. Phantom conjugation — Kriol is largely uninflected; Portuguese ASR will invent tense agreement that was never spoken
3. Village-name destruction — Balanta and Manjaco toponyms are mapped to nearest Portuguese phonetic neighbors
4. Code-switch collapse — mid-sentence Balanta→Kriol→Portuguese code-switching (the cashew-belt register) is flattened to monolingual Portuguese with ~40%+ semantic drift

None of these failure modes are visible to a non-Portuguese-reader — they pass plausibility checks. This is the confidently-wrong failure surface that Botspeak's critical evaluation pillar must be redesigned around for Guinea-Bissau.

What a well-formed oral prompt looks like in Kriol. Following the Task-Context-Constraint model but adapted for Kriol's serial-verb structure:

"Claude, kura: N'misti pa bu skribi un papil di pagamentu. N'kunpra tres saku di kastanha na tabanka di Bissorã, preço mil e kinyentus kada saku. Bota data di aos. Skribi-l kurtu, pa nha xefe entendi."

(Claude, listen: I want you to write a payment paper. I bought three bags of cashew in Bissorã village, price 1500 each. Put today's date. Write it short, so my boss understands.)

The Kriol kura ("listen") as a wake-marker is Inferred more reliable than imported English/Portuguese wake-words; it is already the discourse-opening particle speakers use when dictating to a literate intermediary.

Existing analogous deployments. Observed No production voice-AI deployment exists in Kriol as of April 2026. IVR health education in Burkina Faso (30.33% knowledge increase) and Orange Money USSD flows in Senegal demonstrate that non-literate users can reliably direct transactional voice tools when the menu space is constrained. Unverifiable whether Kriol speakers will transfer this competence to open-ended Claude dictation without scaffolding; likely not in Phase 1.

Objective 2 — Simultaneous Literacy Acquisition

Pedagogical frameworks in-country. Observed Guinea-Bissau's adult literacy infrastructure is thin; functional literacy programs have historically run through Catholic missions (Cacheu, Bafatá), Tiniguena's environmental education work, and Fundação Fé e Cooperação. None currently run at scale in Kriol orthography — most default to Portuguese primers, which reproduces the Portuguese Trap at the curriculum level. Inferred any Botspeak literacy-scaffold deployment must first make a language-of-instruction choice: Kriol orthography (contested, non-standardized) or Portuguese (accessible to fewer learners but institutionally recognized). The honest answer is probably bilingual output with Kriol audio read-back and Portuguese written form, letting the learner build visual-phonetic associations toward Portuguese literacy while operating conversationally in Kriol.

Reading-through-listening bridge. Inferred viable, but constrained by the orthography problem. Hearing Claude read back a Portuguese sentence while the text highlights word-by-word is the standard approach; applied to Guinea-Bissau, the learner is bridging Kriol cognition → Portuguese text, which is a translation task as much as a literacy task. This is harder than the monolingual read-through-listening loop documented in Wolof or Bambara contexts.

Oral-to-written translation role. Inferred this is Claude's strongest contribution. Kriol oral traditions — Balanta djidius (storytellers), Manjaco histories, Bijagó female-elder oral records — have no standardized written corpus. Claude as "digital scribe" producing Portuguese transcriptions of Kriol oral input is a genuinely new capability, but only if the Kriol ASR layer works. This is the prerequisite investment, not the product.

Documented literacy-via-digital cases. Observed None at scale in Guinea-Bissau. Adjacent evidence from Cape Verdean Kriolu orthography work suggests that creole literacy programs succeed when anchored in a single domain (health, commerce) rather than general education. Botspeak + Claude should scope to cashew-transaction literacy as the first domain, not "writing" as such.

Objective 3 — Language-Specific NLP Gaps & Interim Architectures

Minimum viable voice interface for Kriol today: a constrained-domain IVR-plus-LLM hybrid. The user speaks Kriol into a fixed-intent frame ("I want to write X about Y for Z"); a small on-device classifier routes to one of ~20 Botspeak templates; Claude fills the template in Portuguese; Kriol TTS reads back the key fields (who, what, how much, when) using pre-recorded phonemes. Open-ended Kriol-to-Portuguese dictation is a Phase 3 capability, gated on corpus collection.

Objective 4 — Community and Group Models

Shared-device interaction design. Inferred individual smartphone ownership in rural Oio/Tombali is below 25%; group use via the cashew aggregator's device is the realistic access model. The Botspeak interaction must therefore support multi-speaker sessions — the aggregator holds the device, farmers dictate their own entries, and the aggregator validates orally in front of the group. This is closer to a public-notary workflow than to a private writing assistant.

Literate intermediaries. Observed In the cashew belt, the aggregator (djumbai organizer, often Balanta or Manjaco, sometimes Lebanese or Indian merchant intermediary) is the de facto literate intermediary. On the Bijagós, the Tiniguena NGO field agent and the Catholic mission catechist fill this role. In Bafatá/Gabú, Fula religious teachers (Qur'anic schools) are the trust-gatekeepers for any adult education tool. Botspeak's "human supervisor of the AI" role maps onto this intermediary, not the end-user directly — at least in Phase 1.

Oral community validation. Inferred Group listening sessions where Claude's output is read aloud to a farmer cohort and validated collectively map directly onto the existing djumbai cashew-sale ceremony, where prices and weights are already announced publicly for witness. This is the correct substitute for individual critical reading — and it is culturally native, not imported.

Trust dynamics. Observed Guinea-Bissau carries: (1) narco-state legacy distrust of any tool that records transactions (farmers and aggregators both have reasons to fear CENTIF-GB scrutiny); (2) post-coup distrust of state-adjacent tools — 9+ coups mean any product that looks government-endorsed is politically volatile; (3) on the Bijagós, a specific distrust of mainland institutions including Bissau itself. The trust architecture must be explicitly non-state, explicitly non-surveillance, explicitly aggregator-endorsed in the cashew belt and female-elder-endorsed in the Bijagós. Anchoring the tool in BCEAO-regulated rails for any financial flows — and in NGO partnerships (Tiniguena, Catholic mission) for literacy flows — is the only credible path.

Objective 5 — Writing Pedagogy Tension

Scaffold versus substitute. Inferred The scaffold-vs-substitute tension is less acute in Guinea-Bissau than in post-literacy Northern contexts, because the realistic user is not trying to become a Portuguese writer — they are trying to produce a single class of documents (payment records, formal letters, health petitions) that they currently cannot produce at all. The substitute risk is lower when the baseline is "no document exists" rather than "document exists, user wrote it themselves." The genuine pedagogical question is whether Kriol oral composition skill transfers into Portuguese written supervision skill — the Botspeak claim — and the honest answer is Unverifiable without field cohorts.

Productive struggle threshold. Inferred The friction should sit in the evaluation step, not the generation step. The learner should struggle over: did Claude get the village name right? Did Claude get the weight right? Is the tone respectful for a letter to a regional governor? These are judgment tasks the learner can perform orally, against their own mental model, without needing to read Portuguese. This is the actual skill Botspeak teaches, and it is the skill that transfers.

Oral-composition bridges. Observed Guinea-Bissau has rich oral-composition traditions — Balanta kumba ceremonial speech, Manjaco ancestral invocations, Kriol storytelling on state radio. Inferred Using Claude as "apprentice storyteller" works better here than as "apprentice writer": the user dictates a story, Claude produces a Portuguese transcription, the user validates orally against the community. The written artifact is a byproduct.

Assessment approaches. Inferred Assess growth in: (1) number of iterative prompt refinements before approving output; (2) accuracy of plausibility audits against known-seeded errors (did they catch the wrong village name?); (3) willingness to reject Claude output and redictate. None of these require the learner to write.

4. Case Studies

Case Study 1 — The Oio Cashew Aggregator

Malam Ntchala, 44, male, Farim (Oio region, cashew heartland). Languages: Kriol (primary), Balanta (native), basic Portuguese comprehension, non-literate in Portuguese. Cashew aggregator — buys from ~60 smallholder farmers across four tabankas during the Mar–Jun harvest; sells to a Lebanese exporter in Bissau.

Access: Personal Android smartphone (TECNO Spark, 2GB RAM) used for Orange Money and WhatsApp; 4G intermittent outside Farim town. Malam asks Claude to produce farmer-by-farmer payment records (village, weight, CFA amount, date); end-of-week rollup for the exporter; occasional formal letter in Portuguese when a farmer disputes a weight.

Voice prompt in Kriol:

"Claude, kura: N'paga Fatumata Mané, tabanka di Bissorã, sinku saku, setenta kilu kada saku, preço mil e kinyentus pa kilu. Data di aos, dose di abril. Bota tudu na un papil, skribi nomi di tabanka dretu."

Claude output format: A Portuguese-text receipt with bolded numeric fields (quantity, weight, unit price, total, date), village name in original Kriol spelling (not lusophonized), and a Kriol audio read-back that explicitly speaks back the village name, the weight, and the total CFA amount for Malam to validate against his own memory before sending.

Literacy acquisition: Malam builds visual recognition of the Portuguese numerals and the four village names he uses most often. Productive struggle sits in catching ASR errors on Balanta village names — Claude will want to write "Bissorão" for Bissorã; Malam must learn to hear this error in the read-back and force correction. Observable progress indicators: reduction in his "redictate from scratch" rate, increase in targeted correction rate ("no, not Bissorão, Bissorã"), eventual willingness to send receipts without calling his literate nephew to verify.

Endorsement path: Malam's exporter (the Lebanese merchant in Bissau) is the pragmatic gatekeeper — if the exporter accepts Claude-generated receipts as valid trade documents, Malam uses them; if not, they are worthless. The endorsement ceremony is commercial, not traditional. Secondary endorsement: the Balanta council of elders in Bissorã must understand what the tool records and why, or farmers will refuse to be "written down." This requires a Fanado-aware explanation — Unverifiable whether the council will distinguish Claude's records from state-adjacent surveillance without specific framing.

Reciprocal obligation: Once introduced, the tool becomes part of how Malam's farmer network expects to be paid. Withdrawing it mid-season is not an option. Deploy in February or not at all this cycle.

Case Study 2 — The Bijagós Female Elder

N'Bessene Okanga, 58, female, Canhabaque island (Bijagós archipelago). Languages: Bijagó (primary), Kriol (fluent, second language), no Portuguese. Role: okinka (female elder with ceremonial and economic authority); coordinates a women's oyster-harvesting collective; de facto financial decision-maker for ~30 households.

Access: Tiniguena-provided shared tablet (Samsung A-series, 4G when in Bubaque, offline on Canhabaque); boat trip to Bubaque every 8–12 days. N'Bessene asks Claude to produce records of oyster-harvest weights and sale prices, and a formal letter to the regional government in Bissau requesting dike repairs against saltwater intrusion into the rice fields.

Voice prompt in Kriol (N'Bessene uses Kriol with Claude, Bijagó for community deliberation):

"Claude, skuta: Mininus di nha tabanka pega dus mil kilu di ostra na luna pasadu. Bindi na Bubaque, preço tres santus franku pa kilu. Skribi tudu na papil pa nha mostra na reuniãu di mindjeris. Dipus, skribi un karta pa governador, pa el manda konserta diki — awa salgadu ta mata arus."

Claude output format: Offline-capable — the tablet caches Claude's Portuguese output locally and syncs when N'Bessene reaches Bubaque. A Kriol audio summary plays immediately for validation in the village meeting; the Portuguese letter is read aloud by the Tiniguena field agent only after N'Bessene has approved the Kriol version. Extended offline architecture is mandatory — days, not hours.

Literacy acquisition: N'Bessene is not the target literacy learner — her authority does not depend on reading Portuguese. The literacy beneficiary is the younger Tiniguena-trained facilitator, who learns to supervise Claude's output against N'Bessene's validation. Productive struggle: N'Bessene's critical evaluation is oral and cultural — is this letter respectful enough for a regional governor? Does it name the right saints and ancestors? This is a supervision skill Botspeak explicitly teaches, applied at the highest available register.

Endorsement path: Bijagó female authority is the entry point, not an afterthought. Cold approach to Canhabaque is inadvisable; introduction must run through Tiniguena's existing mangrove-conservation partnership, which already has N'Bessene's trust. The endorsement ceremony is a formal presentation to the island's female council, in Bijagó (translated from Kriol), with explicit explanation of what the tablet records, who sees the recording, and what happens to the audio. The council will ask who owns the data. The answer must be credible and non-state.

Reciprocal obligation: Tiniguena inherits responsibility for tool continuity. If Claude becomes unavailable or Tiniguena loses funding, the women's collective loses a governance tool that the island's rice-field survival may depend on. This is a serious obligation; it should not be taken on without a multi-year commitment.

5. Strategic Deployment Brief

Executive Finding

Botspeak × Claude in Guinea-Bissau is not a translation of the Western framework — it is a different product sharing the same conceptual backbone. The supervision skills Botspeak teaches (specify, delegate, evaluate, judge) map well onto Kriol oral culture and the aggregator/female-elder authority structures that already validate information orally. The generation layer does not: Kriol has no production ASR, Portuguese ASR fails confidently on Kriol, and literacy rates in the cashew belt and Bijagós make text-first interaction a non-starter. The product that ships in Guinea-Bissau is a Kriol-voice supervisory frame for Claude's Portuguese output, scoped initially to cashew-transaction documentation (Oio/Bafatá) and mangrove/rice advocacy correspondence (Bijagós).

Dimension Priorities (ranked by deployment risk)

1. Linguistic architecture — Kriol ASR/TTS stack is the single largest investment and the gating prerequisite for anything beyond templated IVR
2. Cultural architecture — aggregator-first in the cashew belt, female-elder-first in the Bijagós, non-state trust framing everywhere
3. Infrastructure — cashew-season deployment window is non-negotiable; miss February and wait a year
4. Regulatory — BCEAO anchor, CENTIF-GB awareness, no ministry-dependent architecture
5. Interface — group-listening validation as the core interaction, not individual read-through
6. Financial — only relevant if Botspeak is bundled with payment; if so, enhanced AML/CFT applies

Phased Roadmap

Political risk gates. Every phase after Phase 0 is gated on: (a) BCEAO regulatory continuity, (b) Tiniguena partnership continuity on the Bijagós, (c) no coup cycle disrupting the November–February build window. If (c) happens, phases slide by a full cashew cycle — one year.

Next Steps

1. Commission a 90-day field scoping trip: Farim + Bissorã (cashew belt) and Bubaque + Canhabaque (Bijagós), in partnership with Tiniguena and a Catholic mission contact in Bafatá
2. Kriol corpus RFP — scoped to 500+ hours, domain-bounded to cashew transactions and formal correspondence
3. Legal review of CENTIF-GB reporting obligations for any voice recordings containing transaction data
4. BCEAO briefing on the data residency architecture before any deployment begins

---

About this report. This is a fictional adaptation study produced as a demonstration of the GEBA methodology applied to AI literacy tool deployment. It was produced by GEBA's AI adaptation framework, not by Anthropic or Claude. The Botspeak framework is developed by Irreducibly Human. Claude is a product of Anthropic. Neither organization commissioned, reviewed, or endorsed this report. All case study profiles are fictional. All deployment recommendations are illustrative examples of adaptation analysis methodology.

Framework: GEBA — Guinea-Bissau AI Adaptation Consulting
Report type: Botspeak × Claude AI Literacy Adaptation Study
For the full framework methodology and other market audits: MoctarDatt.com